© 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. 108359
    Prev
    Next
    INDEX
    Explanations

    International Brotherhood of

    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
     house
    -0.74
     House
    -0.71
     School
    -0.68
    perk
    -0.68
    Offers
    -0.67
     nitrogen
    -0.67
    谩
    -0.67
    ᛫
    -0.66
    geschenk
    -0.66
     chce
    -0.66
    POSITIVE LOGITS
     fiori
    0.71
    Exports
    0.71
    uelo
    0.68
     corners
    0.64
    зі
    0.64
    liss
    0.63
    fid
    0.62
    唯一的
    0.62
     annulus
    0.62
     bouts
    0.61
    Activations Density 0.059%

    No Known Activations