© 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. 71864
    Prev
    Next
    INDEX
    Explanations

    go import paths

    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
    🛇
    -1.82
     Gaulle
    -1.77
     onPostExecute
    -1.66
    rophi
    -1.62
    ☫
    -1.59
    детский
    -1.58
    odyear
    -1.57
    🫃
    -1.55
     hvilke
    -1.55
    ledad
    -1.53
    POSITIVE LOGITS
     they
    1.91
     則
    1.89
    T
    1.57
     There
    1.55
    </em>
    1.55
    Through
    1.55
     However
    1.54
     herren
    1.52
     That
    1.51
    eniging
    1.50
    Activations Density 0.023%

    No Known Activations