© 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. 12-GEMMASCOPE-2-RES-262K
    7. 44481
    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
    りの
    1.07
    ის
    1.00
    ۀ
    0.98
     Rong
    0.96
    Koi
    0.92
     Lexington
    0.91
    บน
    0.91
     Koi
    0.91
    onian
    0.90
    стин
    0.90
    POSITIVE LOGITS
    a
    1.06
    χ
    1.02
    𝓰
    0.92
    ან
    0.81
     amounted
    0.80
    一定的
    0.80
    러
    0.80
    compatible
    0.79
    gène
    0.76
     zakresie
    0.75
    Activations Density 0.000%

    No Known Activations