Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 149343
    Prev
    Next
    INDEX
    Explanations

    hex color codes or "or" conjunctions

    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_29_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
    indak
    0.76
    rin
    0.74
    攽
    0.71
    there
    0.71
    strict
    0.69
     байланы
    0.68
     ack
    0.67
    돔
    0.67
    getInt
    0.67
    ranet
    0.66
    POSITIVE LOGITS
     किंवा
    0.99
     или
    0.99
    หรือ
    0.97
     or
    0.94
     અથવા
    0.94
    或
    0.93
    材
    0.91
     বা
    0.90
     یا
    0.90
     extracted
    0.89
    Activations Density 0.001%

    No Known Activations