© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66169
    Prev
    Next
    INDEX
    Explanations

    legal documents and agreements

    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_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
    cams
    -0.73
    リクエスト
    -0.71
    cortico
    -0.69
    grams
    -0.69
    ọt
    -0.68
     Kühl
    -0.67
    딪
    -0.67
    cab
    -0.67
    ડ
    -0.67
     thậm
    -0.67
    POSITIVE LOGITS
    Signatures
    0.84
    SIGN
    0.82
     intention
    0.81
     Exhibit
    0.76
     Signature
    0.75
     SIGN
    0.75
    balo
    0.73
    PROXY
    0.73
    intention
    0.72
    inten
    0.71
    Activations Density 0.018%

    No Known Activations