© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 24999
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers and warranties

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects vocabulary typical of legal disclaimers and software license texts (e.g. words about permissions, warranties, risks, accuracy, copying, distribution, and liability).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    legal disclaimers and terms related to accuracy, liability, and representations.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @jyhe0408

    disclaimer and license fine‑print language, especially statements about permissions, accuracy, warranties/liabilities, and forward‑looking risks.

    oai_token-act-pair · gpt-5
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     проведение
    -1.32
    providedIn
    -1.31
     
    -1.21
    dienne
    -1.20
     jornalista
    -1.19
     Η
    -1.15
     (‘
    -1.15
    ৳
    -1.12
    itamos
    -1.12
    )];
    -1.09
    POSITIVE LOGITS
     or
    2.72
     and
    2.33
     или
    1.51
    や
    1.49
    หรือ
    1.45
     یا
    1.30
    Expedia
    1.19
     bepaald
    1.13
     prachtig
    1.13
    小說
    1.12
    Activations Density 0.070%

    No Known Activations