© 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. 90427
    Prev
    Next
    INDEX
    Explanations

    AFP Getty Images attribution

    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
    divide
    -0.77
    機能
    -0.72
     divide
    -0.72
    attach
    -0.71
    esi
    -0.70
     Pos
    -0.70
    consume
    -0.70
     マー
    -0.70
     мамы
    -0.69
     Chern
    -0.69
    POSITIVE LOGITS
     fet
    0.76
    Treas
    0.73
     nueva
    0.71
     Viitattu
    0.71
     via
    0.71
    SLP
    0.69
    ercises
    0.69
    ptos
    0.68
    comando
    0.67
    Tare
    0.67
    Activations Density 0.050%

    No Known Activations