© 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. 44462
    Prev
    Next
    INDEX
    Explanations

    typing differences

    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
     voltou
    1.01
    ｭ
    0.94
    Y
    0.92
     ciertas
    0.91
    Hmm
    0.88
    om
    0.87
    A
    0.87
     soluções
    0.86
    reviewed
    0.86
     tuvieron
    0.86
    POSITIVE LOGITS
    εια
    0.79
    <0xA8>
    0.77
     Floral
    0.66
     Daph
    0.64
     ла
    0.61
    ណ៍
    0.61
     clair
    0.60
    ोग्राम
    0.60
    енера
    0.60
    がか
    0.60
    Activations Density 0.000%

    No Known Activations