© 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. 34770
    Prev
    Next
    INDEX
    Explanations

    free software and license

    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
     друзьями
    -0.74
    chtigkeit
    -0.72
    rock
    -0.72
    WithString
    -0.70
     أعلى
    -0.66
    cije
    -0.65
     Really
    -0.65
    ⫺
    -0.65
    setResult
    -0.65
    部位
    -0.65
    POSITIVE LOGITS
    mpotent
    0.79
    ioms
    0.73
    cidas
    0.70
    빠
    0.68
    peaceful
    0.68
     bronz
    0.68
    Wien
    0.68
     needle
    0.66
     pleasant
    0.65
    Sediment
    0.65
    Activations Density 0.039%

    No Known Activations