© 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. 160305
    Prev
    Next
    INDEX
    Explanations

    word continuations

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

    data lake format and sensors

    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
     يكن
    0.46
     EDM
    0.45
     feet
    0.45
     bends
    0.45
    不如
    0.44
    вки
    0.44
     Bundesliga
    0.44
     V
    0.43
     vacancies
    0.43
     cerebral
    0.43
    POSITIVE LOGITS
     핸
    0.48
     टमाटर
    0.48
     गी
    0.47
    ३
    0.47
    öst
    0.47
    お知らせ
    0.47
    メッセージ
    0.46
     лі
    0.46
     دیوار
    0.46
     सब्जियों
    0.45
    Activations Density 0.001%

    No Known Activations