© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103332
    Prev
    Next
    INDEX
    Explanations

    Q: questions about programming

    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
    ochemical
    -0.87
    privateKey
    -0.82
    uparrow
    -0.82
     MAPS
    -0.81
     LES
    -0.79
    zigen
    -0.79
    Harmful
    -0.79
    빡
    -0.76
     DED
    -0.76
    ufer
    -0.75
    POSITIVE LOGITS
     Grunds
    0.90
    mici
    0.84
    Green
    0.79
     Green
    0.79
    ல்ல
    0.78
     Allen
    0.77
    Pu
    0.74
    scrub
    0.74
    -=
    0.73
    Profit
    0.73
    Activations Density 0.003%

    No Known Activations