© 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. 67179
    Prev
    Next
    INDEX
    Explanations

    equipped with

    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
     were
    -3.47
    $,
    -2.59
    脔
    -2.50
    菒
    -2.34
    .“
    -2.34
    eniem
    -2.31
    int
    -2.25
    ፑ
    -2.20
    }$,
    -2.19
     výraz
    -2.14
    POSITIVE LOGITS
     was
    2.52
     rús
    2.52
    先は
    2.47
    はこんな感じ
    2.44
     waren
    2.31
    鬓
    2.16
    䊐
    2.14
    閡
    2.14
    formatie
    2.11
     arkas
    2.11
    Activations Density 0.004%

    No Known Activations