Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6214
    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
     teclado
    0.87
     ткани
    0.87
     ткань
    0.86
    wicklung
    0.86
    ylinder
    0.85
     платье
    0.82
    🖒
    0.82
    punkt
    0.80
    cribed
    0.80
    торы
    0.79
    POSITIVE LOGITS
    1
    0.96
    お
    0.89
    로
    0.88
    2
    0.85
    日
    0.84
     otten
    0.81
    3
    0.80
    ሮችን
    0.80
    吉祥
    0.78
    上
    0.78
    Activations Density 0.000%

    No Known Activations