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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1921
    Prev
    Next
    INDEX
    Explanations

    oven temperature (e.g., 350°F/175°C)

    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_16k_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
    іль
    1.05
    род
    1.01
    ди
    0.99
    ی
    0.93
    ことで
    0.92
    اب
    0.87
    دي
    0.87
    e
    0.86
    не
    0.85
    ski
    0.83
    POSITIVE LOGITS
    的和
    0.98
     unambiguously
    0.84
    ı
    0.83
    梩
    0.80
     $("<
    0.79
    裴
    0.79
     devised
    0.78
    istic
    0.77
    regation
    0.77
     감소
    0.77
    Activations Density 0.002%

    No Known Activations