© 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. 162174
    Prev
    Next
    INDEX
    Explanations

    lists, categories, or items

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

    description

    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
    -
    0.42
     באמצעות
    0.42
    bas
    0.41
     molding
    0.40
    வின்
    0.40
     chast
    0.40
    '
    0.40
     de
    0.40
     discretization
    0.40
     obeys
    0.39
    POSITIVE LOGITS
    NSInteger
    0.50
    竞争力
    0.49
    兖
    0.49
    ларга
    0.48
    ρέ
    0.47
    linkCell
    0.47
     motionProxy
    0.47
    集
    0.47
    क्वल
    0.45
    痫
    0.45
    Activations Density 0.000%

    No Known Activations