© 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. 855
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Searching
    0.88
    Searching
    0.86
     Mabel
    0.82
     शायद
    0.79
     SEARCH
    0.79
     Much
    0.78
     б
    0.77
     Cur
    0.77
    에는
    0.77
     Smit
    0.77
    POSITIVE LOGITS
     wspól
    0.76
    謐
    0.73
    ంగా
    0.73
    。)
    0.72
     sparen
    0.70
    れた
    0.70
    ip
    0.70
    ຫຼື
    0.70
     noirâtres
    0.68
    लट्
    0.68
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.