© 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. 62906
    Prev
    Next
    INDEX
    Explanations

    redistribute and modify

    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
     people
    -0.96
     because
    -0.90
     monthly
    -0.79
    ESSA
    -0.79
     October
    -0.75
     well
    -0.75
     Annotation
    -0.74
     double
    -0.74
     first
    -0.73
     only
    -0.73
    POSITIVE LOGITS
     bidders
    1.01
     Ub
    0.87
    configurable
    0.87
    EXP
    0.86
     ub
    0.85
    Ub
    0.85
     bidder
    0.82
    Bid
    0.81
    him
    0.81
     Bid
    0.81
    Activations Density 0.001%

    No Known Activations