© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2205
    Prev
    Next
    INDEX
    Explanations

    seriously):

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
     Ио
    0.77
     Aunque
    0.73
     Evaluación
    0.70
     Toutefois
    0.69
    Еще
    0.69
     Namun
    0.68
     Сим
    0.67
    <unused2157>
    0.67
     Га
    0.67
    <unused2133>
    0.67
    POSITIVE LOGITS
     thereof
    0.73
    ukin
    0.57
     celle
    0.56
     ones
    0.55
    それに
    0.54
    baliknya
    0.54
    場合に
    0.53
     거기
    0.52
     उसमे
    0.52
    后者
    0.52
    Activations Density 4.530%

    No Known Activations