© 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. 34-GEMMASCOPE-RES-131K
    7. 117674
    Prev
    Next
    INDEX
    Explanations

    italics using asterisks

    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_34/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
    𝗌
    -0.89
    厢
    -0.80
     fully
    -0.75
    嬤
    -0.75
    阖
    -0.75
    inkscape
    -0.75
    스템
    -0.71
    visits
    -0.70
    <tr>
    -0.69
    𝙱
    -0.69
    POSITIVE LOGITS
    haz
    0.90
     ориенти
    0.88
     qualifi
    0.81
    mung
    0.81
    uhan
    0.80
     HIGHER
    0.79
     Sarkar
    0.79
     insign
    0.78
    之路
    0.78
    eel
    0.78
    Activations Density 0.042%

    No Known Activations