© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 8817
    Prev
    Next
    INDEX
    Explanations

    both/either

    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_24_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
    antiene
    0.61
    屼
    0.60
     intimid
    0.59
     Kỳ
    0.58
     eignet
    0.58
    ान
    0.57
     परिचित
    0.56
     địch
    0.56
    遊
    0.55
    vendors
    0.54
    POSITIVE LOGITS
    !।
    0.67
    !).
    0.67
    !!!
    0.66
     salga
    0.66
    !
    0.63
     everything
    0.62
    :].
    0.61
     чтобы
    0.60
    ].
    0.60
     after
    0.59
    Activations Density 0.002%

    No Known Activations