© 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. 84999
    Prev
    Next
    INDEX
    Explanations

    Some possible

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

    Landmarks

    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
     フランス
    0.54
     ゴ
    0.54
    material
    0.49
    leurs
    0.49
    observer
    0.49
    pressed
    0.48
     ފ
    0.47
     ガ
    0.47
    cliente
    0.47
     vade
    0.46
    POSITIVE LOGITS
    казыва
    0.49
    ชม
    0.48
    ิต
    0.46
     conclusively
    0.46
    ต
    0.45
    벼
    0.45
    пто
    0.45
    зви
    0.44
    сия
    0.44
     prioritise
    0.43
    Activations Density 0.000%

    No Known Activations