© 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. 121326
    Prev
    Next
    INDEX
    Explanations

    download manual online

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

    confirming understanding or status

    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
     書い
    0.48
     정
    0.48
    屡
    0.46
    ゲーム
    0.46
     Blunt
    0.46
    руется
    0.46
     хватает
    0.45
     書
    0.45
     coração
    0.45
    게임
    0.45
    POSITIVE LOGITS
    lak
    0.45
    Essex
    0.44
    stoffen
    0.42
    Label
    0.42
    hub
    0.42
     pharmaceuticals
    0.42
    an
    0.41
    stedt
    0.41
     vores
    0.40
    stor
    0.40
    Activations Density 0.000%

    No Known Activations