© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110633
    Prev
    Next
    INDEX
    Explanations

    names and ships

    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
     Бю
    -0.77
     хотели
    -0.77
     захворю
    -0.77
    umbus
    -0.72
    igail
    -0.71
    anyak
    -0.70
     oleju
    -0.69
    tena
    -0.68
    arika
    -0.68
    gina
    -0.67
    POSITIVE LOGITS
     tives
    0.96
     Steer
    0.81
     livestock
    0.78
     steer
    0.77
     turbine
    0.73
     RIM
    0.73
    坝
    0.72
    noscript
    0.71
     tér
    0.71
     paddle
    0.71
    Activations Density 0.016%

    No Known Activations