© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70399
    Prev
    Next
    INDEX
    Explanations

    bibliography and notes sections

    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
     |
    -0.95
    resave
    -0.93
     https
    -0.90
    getWriter
    -0.87
    помо
    -0.87
    arang
    -0.86
     Nedir
    -0.85
    войства
    -0.82
     Пор
    -0.82
     Property
    -0.82
    POSITIVE LOGITS
    🤬
    1.24
    😢
    1.11
    😵
    1.03
     kopf
    1.02
     maduro
    1.00
    ❓
    1.00
    😖
    1.00
     fiable
    0.98
    frist
    0.98
    mex
    0.95
    Activations Density 0.001%

    No Known Activations