© 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. 10-GEMMASCOPE-RES-131K
    7. 102533
    Prev
    Next
    INDEX
    Explanations

    Cheltenham, Farmington, sectarian discourse

    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_10/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
    {
    -3.05
    他說
    -2.78
    </h2>
    -2.41
    聽到
    -2.34
    ⚌
    -2.30
    幫助
    -2.16
    這麼
    -2.14
    t
    -2.13
     was
    -2.11
    レンタ
    -2.11
    POSITIVE LOGITS
    ":
    2.75
    呖
    2.64
     jos
    2.48
    亊
    2.47
    捽
    2.39
    百姓
    2.36
    Ꮨ
    2.34
    呿
    2.33
    草原
    2.33
     prioriti
    2.33
    Activations Density 0.022%

    No Known Activations