© 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. 30846
    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
     sommeil
    0.77
     payers
    0.71
     béné
    0.71
     cump
    0.70
     Bonifacio
    0.70
    ▀
    0.70
    )-$
    0.69
     simil
    0.68
    pho
    0.68
     endure
    0.68
    POSITIVE LOGITS
    Y
    0.88
     ആണ്
    0.86
    ta
    0.80
    stice
    0.80
    X
    0.80
     číslo
    0.76
    に
    0.76
    tal
    0.73
    tic
    0.72
    이나
    0.71
    Activations Density 0.000%

    No Known Activations