© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72721
    Prev
    Next
    INDEX
    Explanations

    legal responsibility and liability

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
     pernic
    -1.37
     applau
    -1.34
    IALLY
    -1.32
    grees
    -1.31
     mauva
    -1.24
     pietre
    -1.24
    ेशन
    -1.23
    agerie
    -1.21
     forment
    -1.21
     AMAZING
    -1.20
    POSITIVE LOGITS
     or
    1.76
     liability
    1.42
     legal
    1.35
     both
    1.32
     case
    1.25
     responsabilité
    1.23
     customers
    1.23
    וּ
    1.19
     risk
    1.17
    ּוֹ
    1.16
    Activations Density 0.036%

    No Known Activations