© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1839
    Prev
    Next
    INDEX
    Explanations

    reasoning for explanations

    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_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
     nonlinearity
    0.79
    这段
    0.73
     nonlinear
    0.72
    凵
    0.71
     debates
    0.71
    disp
    0.71
    多个
    0.71
     thousand
    0.70
     hundred
    0.70
    Wr
    0.70
    POSITIVE LOGITS
    ographiques
    0.74
    </h4>
    0.71
     щодо
    0.71
    </h3>
    0.70
    ใจ
    0.69
     pracov
    0.69
     дорогу
    0.69
    ompany
    0.68
     Cinta
    0.67
    </h1>
    0.67
    Activations Density 0.000%

    No Known Activations