© 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. 236310
    Prev
    Next
    INDEX
    Explanations

    entities and their common followers

    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
     prima
    0.50
    ₪
    0.44
     warehouse
    0.44
    總
    0.44
     hade
    0.42
    遺跡
    0.41
    У
    0.41
    蠟
    0.41
     tinted
    0.41
     Commissioner
    0.40
    POSITIVE LOGITS
     ஆனால்
    0.54
     لیکن
    0.50
     නමුත්
    0.49
     പക്ഷേ
    0.49
     लेकिन
    0.48
    <unused609>
    0.47
     eşit
    0.46
    लेकिन
    0.46
     kés
    0.46
    咵
    0.46
    Activations Density 0.000%

    No Known Activations