© 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. 118373
    Prev
    Next
    INDEX
    Explanations

    integrals to infinity

    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
    _{[
    -0.74
    ൃ
    -0.71
     fear
    -0.71
     îna
    -0.69
     arc
    -0.69
    òm
    -0.69
    年月
    -0.67
    複数
    -0.67
     பெ
    -0.66
    vsk
    -0.66
    POSITIVE LOGITS
     $-\
    1.98
    (-\
    1.93
    _{-\
    1.82
    $-\
    1.69
    =-\
    1.32
    infinite
    1.23
     infinite
    1.20
    {-\
    1.17
    Infinite
    1.14
     (−
    1.10
    Activations Density 0.052%

    No Known Activations