© 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. 6899
    Prev
    Next
    INDEX
    Explanations

    licensing conditions and code snippets

    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
    REM
    -0.85
    movie
    -0.80
    tomy
    -0.75
    MG
    -0.75
    御
    -0.75
    ample
    -0.74
     Gemeinde
    -0.70
    REQUIRE
    -0.70
     sá
    -0.69
     momentary
    -0.69
    POSITIVE LOGITS
     Stir
    0.83
    ⡄
    0.77
    深夜
    0.76
    下が
    0.73
    ド
    0.72
    Datos
    0.70
    不
    0.69
    ד
    0.68
    DataTo
    0.68
    TALL
    0.67
    Activations Density 0.673%

    No Known Activations