© 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. 4257
    Prev
    Next
    INDEX
    Explanations

    antibody production

    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
    ాన్ని
    1.98
    پلز
    1.94
    عا
    1.70
    ão
    1.67
    ם
    1.67
    りました
    1.66
    嶷
    1.66
    یع
    1.64
    לות
    1.63
    ção
    1.60
    POSITIVE LOGITS
    ਰ
    1.98
    and
    1.89
    ри
    1.87
    га
    1.86
    ра
    1.82
    ре
    1.82
    t
    1.78
    ೬
    1.69
     zatim
    1.68
    robi
    1.64
    Activations Density 0.004%

    No Known Activations