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. 3976
    Prev
    Next
    INDEX
    Explanations

    large size

    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
    s
    0.99
    ों
    0.93
    ের
    0.72
    ेष
    0.67
    ים
    0.66
    ությ
    0.66
    తులు
    0.65
    setWindowTitle
    0.65
    this
    0.65
    ifelse
    0.65
    POSITIVE LOGITS
     ageing
    0.87
    ح
    0.80
     spores
    0.79
    нні
    0.77
    да
    0.76
     ascetic
    0.75
    الح
    0.74
     kings
    0.74
     aliments
    0.74
    ни
    0.73
    Activations Density 0.002%

    No Known Activations