© 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. 95831
    Prev
    Next
    INDEX
    Explanations

    details and determining importance

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

    describing athlete, jokes, or traveler from future

    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
    eter
    0.46
     இந்தப்
    0.46
     unteren
    0.44
     ఈ
    0.44
     याबाबत
    0.44
    ブン
    0.43
     فنی
    0.41
     בה
    0.41
     вечером
    0.41
     igualdad
    0.41
    POSITIVE LOGITS
     hassle
    0.44
    ালো
    0.44
    concurrent
    0.44
    contiguous
    0.43
    جهز
    0.43
    notlocked
    0.43
    t
    0.43
    Ī
    0.42
     chromosomes
    0.42
     misty
    0.42
    Activations Density 0.001%

    No Known Activations