© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59494
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and identifiers

    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
     Су
    -0.77
    尙
    -0.74
     deseos
    -0.69
     contenidos
    -0.68
    soft
    -0.68
    うちに
    -0.68
    CGRectMake
    -0.66
     gönder
    -0.66
     živ
    -0.66
    vlá
    -0.65
    POSITIVE LOGITS
     negativa
    0.82
     Bool
    0.80
     препо
    0.79
    ativität
    0.77
     Nicaragua
    0.77
     nef
    0.77
    ENSITY
    0.74
    hausen
    0.73
    ategy
    0.73
     plural
    0.72
    Activations Density 0.010%

    No Known Activations