© 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. 10-GEMMASCOPE-RES-131K
    7. 111752
    Prev
    Next
    INDEX
    Explanations

    lists and conjunctions

    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_10/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
     you
    -2.22
    {
    -1.91
    '
    -1.85
     then
    -1.78
    eronau
    -1.77
     it
    -1.70
    Ã
    -1.67
    ᚔ
    -1.65
     クッション
    -1.63
    却不
    -1.63
    POSITIVE LOGITS
     an
    2.16
    anggaran
    1.79
    𖥦
    1.78
     शुर
    1.77
    Donativos
    1.73
    كاتب
    1.70
     exigencias
    1.66
     costumbres
    1.64
     уже
    1.62
     diğer
    1.60
    Activations Density 0.364%

    No Known Activations