© 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. 6605
    Prev
    Next
    INDEX
    Explanations

    right and

    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
     Dự
    0.72
     Люди
    0.70
    ται
    0.67
    ٠
    0.66
    ૦
    0.66
    ELECTRIC
    0.65
     подро
    0.64
     байланы
    0.64
     आस्ट्रेलिया
    0.63
     เรา
    0.62
    POSITIVE LOGITS
     and
    0.67
    .
    0.61
    ening
    0.61
     enough
    0.55
     happenings
    0.55
    och
    0.52
    .");
    0.52
     सुद्धा
    0.52
    p
    0.52
    خ
    0.51
    Activations Density 0.638%

    No Known Activations