© 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. 93292
    Prev
    Next
    INDEX
    Explanations

    Mechanical equipment; Air India; O'Connor; Blizzard

    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
     in
    -2.80
     to
    -2.20
     on
    -2.09
     or
    -1.83
     from
    -1.78
     because
    -1.77
     for
    -1.76
     usually
    -1.73
     if
    -1.73
     (
    -1.72
    POSITIVE LOGITS
     horrid
    1.71
     molte
    1.66
     tumultuous
    1.56
     Dinas
    1.54
     verschillende
    1.52
    푉
    1.52
     pivotal
    1.51
    <tr>
    1.51
     dismal
    1.50
     abd
    1.50
    Activations Density 0.000%

    No Known Activations