© 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. 107593
    Prev
    Next
    INDEX
    Explanations

    T followed by date or place name

    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
     Bambi
    -0.95
     Infla
    -0.93
    zulegen
    -0.90
    魃
    -0.88
     lage
    -0.87
     vixion
    -0.87
     syns
    -0.87
    雜誌
    -0.86
     tramontina
    -0.86
     Illustrations
    -0.84
    POSITIVE LOGITS
     such
    1.10
     one
    0.93
     However
    0.85
     early
    0.84
     Create
    0.81
    為に
    0.79
     an
    0.78
     trending
    0.77
    نجان
    0.75
     given
    0.75
    Activations Density 0.005%

    No Known Activations