© 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. 85540
    Prev
    Next
    INDEX
    Explanations

    object types and methods

    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
    kurtka
    -1.23
     dager
    -1.20
    sukienka
    -1.20
     ساتھ
    -1.16
     フー
    -1.16
     maravillosa
    -1.15
     مسابقات
    -1.15
    蚰
    -1.13
    ֊
    -1.11
    luft
    -1.09
    POSITIVE LOGITS
     results
    1.44
     things
    1.39
    してみると
    1.38
     specifics
    1.29
    {
    1.26
    \\
    1.25
    n
    1.24
    </
    1.20
     positivas
    1.20
    In
    1.19
    Activations Density 0.071%

    No Known Activations