© 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. 44308
    Prev
    Next
    INDEX
    Explanations

    flamin hots

    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
    ת
    2.16
    т
    2.05
    ت
    2.00
    ف
    1.59
    ৮
    1.57
    для
    1.53
    во
    1.49
    특별시
    1.47
    лив
    1.43
    тара
    1.43
    POSITIVE LOGITS
    h
    1.61
    ar
    1.52
     consequent
    1.51
     envi
    1.48
    ag
    1.47
    ak
    1.47
     ionization
    1.41
     engross
    1.36
    g
    1.36
    ad
    1.34
    Activations Density 0.002%

    No Known Activations