© 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. 10-GEMMASCOPE-RES-131K
    7. 111779
    Prev
    Next
    INDEX
    Explanations

    poop jokes, Anfield, rkhunter, YP LEAD, ®

    np_acts-logits-general · gemini-2.5-flash-lite

    proper nouns and brand names, particularly location names like "Anfield" and technical/product identifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ONESIA
    -2.39
     luxus
    -2.36
    vantaged
    -2.33
     walkway
    -2.31
    OUTUBE
    -2.30
    乆
    -2.20
    噚
    -2.17
    ländern
    -2.16
    戬
    -2.16
    五日
    -2.14
    POSITIVE LOGITS
    ;
    3.36
    x
    3.05
    k
    2.72
    n
    2.70
    ;-
    2.66
    )”
    2.61
    or
    2.56
    j
    2.47
    ”-
    2.45
    [
    2.44
    Activations Density 0.002%

    No Known Activations