© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58683
    Prev
    Next
    INDEX
    Explanations

    document paper sizes

    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
     ferrous
    -0.79
    ashi
    -0.79
    tarjeta
    -0.73
    為何
    -0.72
     bọc
    -0.71
    CardType
    -0.71
    みや
    -0.71
     perished
    -0.70
    גש
    -0.70
     Wheaton
    -0.70
    POSITIVE LOGITS
     PDF
    0.79
    codegen
    0.77
     hende
    0.74
     Coimbatore
    0.70
     Aud
    0.70
     statistik
    0.69
    侵入
    0.69
    skis
    0.69
    Nobel
    0.69
     chanteuse
    0.69
    Activations Density 0.016%

    No Known Activations