© 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. 92268
    Prev
    Next
    INDEX
    Explanations

    ctypes structures and Python code

    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
    ඇ
    -0.79
    gpl
    -0.76
    bbat
    -0.75
    comprar
    -0.73
    딕
    -0.72
     javascript
    -0.72
     secretion
    -0.72
    範囲
    -0.71
    uerta
    -0.69
    imagePath
    -0.69
    POSITIVE LOGITS
     PO
    0.85
    rests
    0.82
     الشرق
    0.78
    図書館
    0.75
     c
    0.72
     by
    0.71
     C
    0.71
    ੱਕ
    0.70
    POINTER
    0.69
     decreasing
    0.68
    Activations Density 0.025%

    No Known Activations