© 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. 2814
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    forcement
    -0.85
    δη
    -0.78
     тому
    -0.75
    MEMORANDUM
    -0.74
     neki
    -0.73
    ❮
    -0.72
    Tudo
    -0.71
    officially
    -0.71
    !("
    -0.71
     hemos
    -0.71
    POSITIVE LOGITS
     Same
    0.89
    ÊNCIAS
    0.88
    같이
    0.87
    샵
    0.85
    migo
    0.79
    "$_
    0.78
     bepaalde
    0.77
    naz
    0.77
     occasionally
    0.77
     Judea
    0.76
    Activations Density 0.140%

    No Known Activations