© 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. 22-GEMMASCOPE-RES-131K
    7. 72165
    Prev
    Next
    INDEX
    Explanations

    technical or programming terms

    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_22/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
    Bella
    -0.85
     بيان
    -0.77
    +(\
    -0.77
    Norge
    -0.76
    מ
    -0.73
    Img
    -0.73
    Lepid
    -0.72
    asn
    -0.72
     筆
    -0.71
    ualla
    -0.71
    POSITIVE LOGITS
    橋本
    0.97
     for
    0.96
    RectF
    0.92
     работать
    0.91
     yüzden
    0.90
     apparten
    0.88
     ubica
    0.86
    WithMany
    0.85
     suspicion
    0.84
    ogeneous
    0.84
    Activations Density 0.068%

    No Known Activations