© 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. 53965
    Prev
    Next
    INDEX
    Explanations

    help over harm

    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
     água
    0.47
    식회사
    0.44
     nô
    0.44
     cubierta
    0.43
     ponte
    0.43
    LLL
    0.42
    릅
    0.41
    ڈا
    0.41
     dată
    0.41
     fres
    0.40
    POSITIVE LOGITS
    ی
    0.57
    د
    0.55
    oy
    0.47
    Ну
    0.46
     ಅರ್ಥ
    0.46
    ع
    0.45
    etter
    0.44
     கி
    0.44
     derogatory
    0.44
    ي
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.