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. 24-GEMMASCOPE-2-RES-16K
    4. 8428
    Prev
    Next
    INDEX
    Explanations

    special characters or lists

    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_24_width_16k_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
    ри
    0.84
    де
    0.74
    ви
    0.73
     (
    0.70
    م
    0.68
    Cancellation
    0.63
    м
    0.63
    με
    0.62
     Cancell
    0.61
    Nueva
    0.61
    POSITIVE LOGITS
     incrível
    0.96
     coisa
    0.95
     helpen
    0.92
     capazes
    0.87
     aproveitar
    0.87
     Beasley
    0.84
     обнаружи
    0.83
     обеспечивает
    0.83
     estabelecer
    0.82
     ajud
    0.82
    Activations Density 0.005%

    No Known Activations