© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35832
    Prev
    Next
    INDEX
    Explanations

    continuous delivery, generate creative, authentication, infinite dimensional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aceut
    0.80
     Wasn
    0.73
    wParam
    0.71
    的な
    0.71
    現象
    0.70
     merchandising
    0.69
    顾问
    0.68
    ('$
    0.68
    ographic
    0.68
    urization
    0.68
    POSITIVE LOGITS
     Союз
    0.79
    лла
    0.77
     foliis
    0.75
    ш
    0.75
    ри
    0.74
     están
    0.73
     що
    0.73
     exces
    0.73
    Ꮬ
    0.73
    മ
    0.72
    Activations Density 0.000%

    No Known Activations