© 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. 107970
    Prev
    Next
    INDEX
    Explanations

    journal articles citations

    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
    書き
    -0.82
     测试
    -0.78
    ttn
    -0.77
    talent
    -0.77
    当时
    -0.77
    tue
    -0.71
     klat
    -0.71
    scription
    -0.71
    _"+
    -0.71
     Hoss
    -0.70
    POSITIVE LOGITS
    ksiä
    0.79
     Comput
    0.79
     Critic
    0.71
    බ
    0.71
    setX
    0.71
     Hill
    0.71
     COMP
    0.70
     Serialize
    0.68
    <0x81>
    0.67
    BRID
    0.67
    Activations Density 0.013%

    No Known Activations