© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3586
    Prev
    Next
    INDEX
    Explanations

    CT, MRI scans

    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
    ak
    1.12
     U
    1.10
    ia
    1.02
     knife
    1.02
     leader
    0.95
     e
    0.92
     captain
    0.92
     F
    0.89
     But
    0.88
     quarter
    0.88
    POSITIVE LOGITS
    ер
    0.98
     диагности
    0.96
    MRI
    0.90
     мыш
    0.88
     оттен
    0.87
    зм
    0.86
    arzt
    0.85
    هم
    0.84
    않
    0.84
     медицин
    0.83
    Activations Density 0.030%

    No Known Activations