© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92322
    Prev
    Next
    INDEX
    Explanations

    Raspberry pi

    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
    怠
    -0.79
    expr
    -0.77
    了口气
    -0.74
     узнать
    -0.73
    OPHER
    -0.71
     الرغم
    -0.71
     fuerza
    -0.71
    :^(
    -0.70
    brasil
    -0.70
     الفيديو
    -0.69
    POSITIVE LOGITS
     covenants
    0.83
    umbu
    0.82
     Bluffs
    0.79
     leetcode
    0.79
    LIM
    0.77
     Sloane
    0.76
     screenshot
    0.76
    :—
    0.75
     criticism
    0.75
     labai
    0.74
    Activations Density 0.001%

    No Known Activations