© 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. 4070
    Prev
    Next
    INDEX
    Explanations

    recent news and updates

    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
    一定的
    1.90
    та
    1.87
     kuće
    1.60
     së
    1.59
     какое
    1.54
    页面存档备份
    1.54
    ви
    1.46
    م
    1.45
    一些
    1.44
     BoxLayout
    1.41
    POSITIVE LOGITS
    made
    1.94
    したり
    1.83
    viet
    1.73
    cit
    1.70
    pizza
    1.69
    تي
    1.60
    moved
    1.59
    َس
    1.59
    mel
    1.57
    ﺒ
    1.57
    Activations Density 0.014%

    No Known Activations