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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54040
    Prev
    Next
    INDEX
    Explanations

    and conditions

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

    The neuron fires on boilerplate legal/license text, especially spotting the “terms and conditions” phrasing in software license headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     its
    -1.30
     mga
    -1.11
    :
    -1.10
     सेमी
    -1.09
     các
    -1.03
    ''
    -1.03
     เว
    -1.03
    '';
    -1.03
    )':
    -1.02
     Matters
    -1.01
    POSITIVE LOGITS
     their
    2.19
    Their
    1.69
     jejich
    1.68
     Their
    1.59
     их
    1.55
     їх
    1.53
     această
    1.38
     навіть
    1.37
    appliquer
    1.34
     उनके
    1.34
    Activations Density 0.374%

    No Known Activations