© 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. 110653
    Prev
    Next
    INDEX
    Explanations

    months

    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
    wadi
    -0.81
    momile
    -0.79
     např
    -0.78
     SATURDAY
    -0.77
     Saturday
    -0.77
    SATURDAY
    -0.73
    drone
    -0.72
    nige
    -0.71
     saturation
    -0.71
     Saturdays
    -0.71
    POSITIVE LOGITS
    GetAsync
    0.78
     generating
    0.73
    Instrument
    0.72
    իվ
    0.72
    痂
    0.71
    vit
    0.71
     coronav
    0.69
    рока
    0.69
     Coronavirus
    0.69
    sca
    0.69
    Activations Density 0.172%

    No Known Activations