© 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. 3675
    Prev
    Next
    INDEX
    Explanations

    code snippets (python, java, javascript)

    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
    م
    0.73
    ر
    0.66
    使用
    0.61
     uses
    0.57
    उंड
    0.54
    ستخدم
    0.54
     製品
    0.54
     Enables
    0.54
     delimiters
    0.54
    可以使用
    0.54
    POSITIVE LOGITS
    the
    0.52
     ❤️
    0.47
    geolocation
    0.47
    👋
    0.46
    ❤️
    0.46
     showered
    0.45
    getSession
    0.45
     regained
    0.45
     rejuvenated
    0.44
    occasione
    0.44
    Activations Density 0.221%

    No Known Activations