© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 53840
    Prev
    Next
    INDEX
    Explanations

    Java collection declarations

    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
     läh
    -0.77
     ज़
    -0.76
    '].'
    -0.75
    にも
    -0.75
     xảy
    -0.73
    Zap
    -0.70
     tuxedo
    -0.70
     Copyright
    -0.69
    layah
    -0.69
    Krie
    -0.69
    POSITIVE LOGITS
     ↑
    1.35
    <>(
    1.02
    <>
    0.92
    Errorf
    0.86
    acheter
    0.84
     SimpleName
    0.79
    tir
    0.77
     другая
    0.77
    !(
    0.76
     illuminating
    0.74
    Activations Density 0.091%

    No Known Activations