© 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. 12-GEMMASCOPE-2-RES-262K
    7. 31052
    Prev
    Next
    INDEX
    Explanations

    asking "right" or "me"

    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_12_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
    𝘀
    1.38
    きて
    1.27
    る
    1.22
    삐
    1.20
    なる
    1.19
    Creo
    1.19
    ➢
    1.17
    п
    1.15
    際
    1.13
    MANIFEST
    1.11
    POSITIVE LOGITS
    ب
    1.73
    ్‌
    1.51
    是我们
    1.38
    acchati
    1.35
    า
    1.34
     desapare
    1.34
     diffraction
    1.32
     beli
    1.30
    yanka
    1.30
    ı
    1.30
    Activations Density 0.001%

    No Known Activations