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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8261
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ки
    0.76
    ⠀⠀
    0.72
    itized
    0.71
    ع
    0.69
    ie
    0.67
    ни
    0.65
    itization
    0.64
    us
    0.62
    да
    0.62
    ো
    0.62
    POSITIVE LOGITS
    ਆਂ
    0.94
    aub
    0.87
    ală
    0.86
     bestellen
    0.85
     aportan
    0.84
    mujer
    0.84
    くちゃ
    0.84
     pemeriksaan
    0.83
    ouvrage
    0.83
     diastere
    0.83
    Activations Density 0.080%

    No Known Activations