© 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. 33399
    Prev
    Next
    INDEX
    Explanations

    credit card, it protects, it was, black magic, it learns

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

    cultural or linguistic specifics

    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
    Adds
    0.54
    onset
    0.47
    iging
    0.46
    I
    0.46
    TodoList
    0.45
    $
    0.45
    ABET
    0.44
    Text
    0.44
    Contents
    0.44
    adds
    0.44
    POSITIVE LOGITS
    嬴
    0.59
     विद्यु
    0.55
     крупней
    0.54
     импуль
    0.54
    ຕະ
    0.53
    Ꮂ
    0.53
    ชัย
    0.52
    χύ
    0.52
     संतुलित
    0.52
     военной
    0.52
    Activations Density 0.000%

    No Known Activations