© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7304
    Prev
    Next
    INDEX
    Explanations

    git commands and workflow

    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
     actual
    -0.76
     befre
    -0.76
    calling
    -0.75
     факуль
    -0.73
    詳細
    -0.72
    actual
    -0.72
     близ
    -0.71
    close
    -0.71
    했습니다
    -0.71
    Peter
    -0.70
    POSITIVE LOGITS
    bson
    0.99
     GI
    0.93
     Gie
    0.90
    جی
    0.89
     gi
    0.88
     ги
    0.84
     Ги
    0.84
    ギ
    0.82
    Gis
    0.81
     Git
    0.80
    Activations Density 0.027%

    No Known Activations