© 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. 30964
    Prev
    Next
    INDEX
    Explanations

    form/make 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_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
    ﺜ
    0.88
    ﺸ
    0.84
    ﻤ
    0.79
    לה
    0.78
    룸
    0.77
     nacido
    0.77
    Ар
    0.76
     뉴스
    0.76
     Cu
    0.75
    峀
    0.75
    POSITIVE LOGITS
    ان
    0.79
    на
    0.78
    ki
    0.75
    awcy
    0.73
     bate
    0.72
     ration
    0.72
     wajib
    0.71
     lui
    0.70
    cell
    0.69
    cite
    0.69
    Activations Density 0.000%

    No Known Activations