© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 196257
    Prev
    Next
    INDEX
    Explanations

    thread, base, effective, first, combination, Evaluation, job, sets

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

    viral video

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supremacy
    0.46
     armas
    0.44
     Übersetzung
    0.43
     argent
    0.42
     %
    0.42
     viewership
    0.42
     (%
    0.41
     punya
    0.41
     memak
    0.41
     influx
    0.40
    POSITIVE LOGITS
    と思いますが
    0.54
    클
    0.49
    楝
    0.48
    살
    0.46
    ᆯ
    0.45
     প্রতিনিধ
    0.45
    श
    0.45
    เล
    0.43
    疥
    0.43
     শিল
    0.42
    Activations Density 0.001%

    No Known Activations