© 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. 115526
    Prev
    Next
    INDEX
    Explanations

    file paths and table operations

    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
    attori
    -0.86
    ｀*)
    -0.78
    infeld
    -0.74
    chaun
    -0.72
    Semua
    -0.70
    abilis
    -0.69
    Фар
    -0.69
    مين
    -0.69
     widened
    -0.69
     miti
    -0.68
    POSITIVE LOGITS
    ående
    0.74
     tmp
    0.73
    AAAAAAAA
    0.71
    getPoint
    0.71
     blocks
    0.71
     latihan
    0.70
     src
    0.69
     gespe
    0.69
    мей
    0.69
    酥
    0.69
    Activations Density 0.036%

    No Known Activations