© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 800
    Prev
    Next
    INDEX
    Explanations

    randomness and probability

    np_acts-logits-general · gemini-2.5-flash-lite

    probability and statistical calculations

    np_acts-logits-general · gemini-2.5-flash-lite

    probability

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ные
    0.62
     І
    0.59
     n
    0.58
     Statue
    0.57
     мебели
    0.56
     UID
    0.55
     Basilica
    0.53
     Argo
    0.53
     opulent
    0.52
     NIO
    0.52
    POSITIVE LOGITS
    CH
    0.65
    確率
    0.63
    SE
    0.62
    probability
    0.61
    DE
    0.60
    Probability
    0.60
    TER
    0.58
    <strong>
    0.55
     probabilities
    0.55
    概率
    0.55
    Activations Density 0.146%

    No Known Activations