© 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. 38655
    Prev
    Next
    INDEX
    Explanations

    checkerboard, school, task, action

    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
    نیا
    0.82
    亩
    0.82
    ни
    0.80
    賴
    0.80
    秪
    0.80
    ຊ
    0.79
    𝘰
    0.77
    𝘣
    0.76
    texas
    0.75
    籵
    0.75
    POSITIVE LOGITS
    :
    0.78
    afe
    0.76
    ์
    0.71
     Bols
    0.70
    ím
    0.68
     आड
    0.68
     PAOK
    0.67
     Scorpio
    0.66
     Bih
    0.66
     PAG
    0.66
    Activations Density 0.000%

    No Known Activations