© 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. 18179
    Prev
    Next
    INDEX
    Explanations

    six hours

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

    articles, colleagues, injuries

    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
     프랑
    0.51
    ೇಯ
    0.47
    ੁ
    0.46
    시
    0.46
     लैस
    0.46
    フランス
    0.46
    ことができます
    0.45
     아닙
    0.45
     obligaciones
    0.45
     BOOKS
    0.45
    POSITIVE LOGITS
    ä
    0.53
    as
    0.53
    ira
    0.52
    ae
    0.51
    uva
    0.51
    at
    0.48
    ches
    0.48
    rát
    0.48
    item
    0.47
    afka
    0.47
    Activations Density 0.000%

    No Known Activations