© 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. 44780
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by actions or consequences

    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
     estrema
    -2.06
     visse
    -1.94
     vorigen
    -1.93
    ).”
    -1.93
    In
    -1.86
     Geografía
    -1.86
    地区
    -1.84
    es
    -1.82
     onor
    -1.77
     occhiali
    -1.77
    POSITIVE LOGITS
    睺
    2.17
     και
    2.06
    และ
    2.03
    ឵
    1.95
    鉛筆
    1.90
    ・・。
    1.87
    戩
    1.84
     и
    1.82
     eficiente
    1.80
    salms
    1.76
    Activations Density 0.028%

    No Known Activations