© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    conditions, cases,conjunctions

    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
    部分を
    -2.03
    tzmann
    -1.91
     ваш
    -1.82
     вашим
    -1.82
     нашей
    -1.81
    YNAMIC
    -1.80
     เรา
    -1.80
                             
    -1.79
     pequena
    -1.78
     acides
    -1.77
    POSITIVE LOGITS
     that
    3.55
     in
    2.98
     at
    2.77
     because
    2.58
     actually
    2.45
     or
    2.44
     on
    2.42
     (
    2.42
     only
    2.41
     if
    2.31
    Activations Density 0.054%

    No Known Activations