© 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. 1400
    Prev
    Next
    INDEX
    Explanations

    parallel, pledge

    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
    nz
    2.17
    ड़ा
    2.02
    нию
    1.91
    nad
    1.83
    pathTemplates
    1.80
    namen
    1.79
    ୍କ
    1.77
    。
    1.74
    ។
    1.74
    🙏🏻
    1.72
    POSITIVE LOGITS
    क
    2.41
    ف
    2.31
    ب
    2.08
    b
    2.06
    ਾ
    1.84
    ческих
    1.77
    h
    1.72
    生素
    1.71
    ী
    1.70
    ח
    1.66
    Activations Density 0.012%

    No Known Activations