Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 562
    Prev
    Next
    INDEX
    Explanations

    Chinese, Japanese, Korean, Hindi, Bengali characters

    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
    ни
    0.98
     serta
    0.97
    ์
    0.88
     CaCl
    0.87
     CEC
    0.83
     Rous
    0.81
     ZIP
    0.80
    很多的
    0.80
    れば
    0.80
     OCD
    0.80
    POSITIVE LOGITS
    '
    1.02
    the
    0.92
    -
    0.86
     sociali
    0.85
    ’
    0.85
    ब
    0.85
    På
    0.84
     nascost
    0.84
    Istituto
    0.83
    Pentru
    0.83
    Activations Density 0.046%

    No Known Activations