© 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. 3462
    Prev
    Next
    INDEX
    Explanations

    numbers with structure

    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
    :
    0.28
     inférieur
    0.27
    는
    0.25
     존재
    0.25
    ي
    0.25
    =
    0.24
    Ϊ
    0.24
     Erectile
    0.24
     ~(
    0.24
     Conjecture
    0.24
    POSITIVE LOGITS
    lifestyle
    0.26
    自助
    0.26
    കളും
    0.25
    menus
    0.25
    strategies
    0.25
     credo
    0.25
    minutes
    0.25
    二十
    0.25
    rails
    0.25
    pipelines
    0.25
    Activations Density 0.011%

    No Known Activations