© 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. 73608
    Prev
    Next
    INDEX
    Explanations

    filter operator or sets

    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
    rcl
    -0.79
    bsc
    -0.74
    khó
    -0.74
     garansi
    -0.72
    suzuki
    -0.70
    unday
    -0.70
     Thunderbird
    -0.70
    rale
    -0.69
     differs
    -0.68
    kowanie
    -0.68
    POSITIVE LOGITS
    ktes
    0.83
    Sam
    0.77
    finish
    0.75
     Monta
    0.75
    fällen
    0.75
     prem
    0.73
     veer
    0.71
     Longitude
    0.70
    argas
    0.69
     vita
    0.69
    Activations Density 0.014%

    No Known Activations