© 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. 25148
    Prev
    Next
    INDEX
    Explanations

    seams and

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

    free, wild, control, dominant

    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
     横
    0.50
    ⵍ
    0.49
    ระบบ
    0.47
    elier
    0.47
     ինչ
    0.45
    横
    0.45
     жер
    0.45
     डीपी
    0.45
     뉴
    0.44
    unstyled
    0.44
    POSITIVE LOGITS
    Food
    0.43
    PRODUCTS
    0.43
    halten
    0.41
    UTH
    0.40
    RESEARCH
    0.39
     PRODUCTS
    0.39
     reactant
    0.39
     Monate
    0.39
     potrav
    0.39
    FOOD
    0.39
    Activations Density 0.000%

    No Known Activations