© 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. 7076
    Prev
    Next
    INDEX
    Explanations

    advice or a pointed end

    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
     —
    -2.69
    甡
    -2.42
     were
    -2.27
    >
    -2.27
    (
    -2.25
     фоне
    -2.23
    而在
    -2.23
     –
    -2.22
     have
    -2.20
    および
    -2.13
    POSITIVE LOGITS
    䉴
    2.69
    揸
    2.59
    鮠
    2.55
    genodigd
    2.55
    Still
    2.47
    ﮦ
    2.39
    詒
    2.33
    嚒
    2.31
    茳
    2.31
     véhic
    2.30
    Activations Density 0.006%

    No Known Activations