© 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. 918
    Prev
    Next
    INDEX
    Explanations

    choosing, providing, or checking something

    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
    ’
    0.80
    ️
    0.64
    ‌ای
    0.64
    ‌تر
    0.63
    )$.
    0.55
    ‌ی
    0.54
    )’
    0.54
    ד
    0.54
    蟀
    0.53
    чиков
    0.52
    POSITIVE LOGITS
    ع
    0.75
    他
    0.73
    redients
    0.62
    ला
    0.57
    то
    0.56
    让
    0.56
    ly
    0.54
     oneself
    0.54
    یا
    0.53
    نن
    0.53
    Activations Density 0.138%

    No Known Activations