© 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. 34-GEMMASCOPE-RES-131K
    7. 91347
    Prev
    Next
    INDEX
    Explanations

    Keene High, White Mountains

    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
     δή
    -0.81
     baro
    -0.78
     thoải
    -0.78
    心臓
    -0.75
    るの
    -0.75
    šiť
    -0.73
     السياسية
    -0.73
    Precautions
    -0.70
    jd
    -0.70
     Nitrate
    -0.70
    POSITIVE LOGITS
     Disk
    0.86
     setw
    0.84
    Disk
    0.77
     convertView
    0.77
     MW
    0.73
    useEffect
    0.72
     Jak
    0.71
    conio
    0.71
     Aus
    0.71
     pow
    0.71
    Activations Density 0.017%

    No Known Activations