© 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. 24-GEMMASCOPE-2-RES-262K
    7. 3362
    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_24_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
    له
    0.73
    偶然
    0.67
    _
    0.65
    된
    0.65
     !=
    0.64
     =
    0.64
    к
    0.64
    ัน
    0.63
    致
    0.62
    喩
    0.61
    POSITIVE LOGITS
     Punk
    0.76
     Fransiya
    0.75
    POINTS
    0.75
    putnik
    0.74
    abbani
    0.73
     Sebastián
    0.73
    irmingham
    0.72
     peroxidation
    0.72
    ಂತ್
    0.72
     меню
    0.71
    Activations Density 0.002%

    No Known Activations