© 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. 110862
    Prev
    Next
    INDEX
    Explanations

    year ranges with a dash

    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
    inska
    -0.81
     Opp
    -0.81
     Gulch
    -0.77
    ဝ
    -0.77
    osexuality
    -0.77
    صدر
    -0.76
    tements
    -0.74
    GetInt
    -0.73
    鏂
    -0.72
    ırlı
    -0.72
    POSITIVE LOGITS
    –
    0.80
    []{
    0.68
    -
    0.66
    Engineers
    0.64
    那我
    0.64
     hyphen
    0.63
    没什么
    0.62
    hacia
    0.62
    Esse
    0.61
    自分に
    0.61
    Activations Density 0.157%

    No Known Activations