© 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. 98165
    Prev
    Next
    INDEX
    Explanations

    character encoding or code comments

    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
    壯
    -0.70
    nikon
    -0.70
    Académie
    -0.68
    మూ
    -0.67
    FTA
    -0.66
    ducks
    -0.65
    winding
    -0.64
    肽
    -0.64
    terrorism
    -0.64
     模
    -0.63
    POSITIVE LOGITS
     synerg
    0.77
     Mahesh
    0.71
    ynki
    0.71
    ית
    0.69
    zyb
    0.68
    hue
    0.67
     منط
    0.66
    gements
    0.65
    aryti
    0.65
     Porn
    0.65
    Activations Density 0.046%

    No Known Activations