© 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. 22-GEMMASCOPE-RES-131K
    7. 65764
    Prev
    Next
    INDEX
    Explanations

    Nebraska Supreme, Studywise

    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_22/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
    <bos>
    -2.13
    🕗
    -1.96
     from
    -1.59
     vermelhas
    -1.59
    řád
    -1.55
    🏢
    -1.54
    方針
    -1.52
    öffentlichen
    -1.48
     岁
    -1.44
     brancas
    -1.41
    POSITIVE LOGITS
    d
    1.79
    া
    1.69
    ほら
    1.66
    A
    1.63
     questa
    1.63
    嵓
    1.62
     dovrebbe
    1.59
    あー
    1.59
    u
    1.56
    ormány
    1.54
    Activations Density 0.001%

    No Known Activations