© 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. 7952
    Prev
    Next
    INDEX
    Explanations

    estimate costs and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    t
    2.50
    m
    2.28
     spree
    1.97
     सारी
    1.95
     immers
    1.84
    n
    1.78
     clues
    1.77
    রুখ
    1.75
    م
    1.75
    熊本
    1.73
    POSITIVE LOGITS
    اب
    2.27
    ні
    2.06
    ں
    1.98
    ди
    1.98
    то
    1.95
    ॉ
    1.83
    Yeni
    1.82
    EN
    1.71
    غ
    1.68
    ї
    1.65
    Activations Density 0.187%

    No Known Activations