© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32765
    Prev
    Next
    INDEX
    Explanations

    code/email addresses with @

    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
    Parmi
    -0.82
    Trichloroethane
    -0.75
     isEqualToString
    -0.73
    Dès
    -0.71
    Cependant
    -0.70
     料
    -0.70
     przec
    -0.69
    torio
    -0.68
     てる
    -0.68
     CLK
    -0.68
    POSITIVE LOGITS
    Na
    0.67
    鄱
    0.66
     ס
    0.66
     Validate
    0.65
     activists
    0.63
    SET
    0.63
    hashes
    0.63
    @\
    0.62
     فإن
    0.62
    ṇa
    0.62
    Activations Density 0.076%

    No Known Activations