© 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. 7925
    Prev
    Next
    INDEX
    Explanations

    important considerations section

    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
    0.89
     з
    0.85
    а
    0.85
    ă
    0.85
     essere
    0.83
     marzo
    0.82
    🇪
    0.82
     Σε
    0.82
    เป็น
    0.80
    கடந்த
    0.80
    POSITIVE LOGITS
     afterlife
    0.83
    arod
    0.81
    otipo
    0.78
     stricter
    0.73
     strictest
    0.72
    ार्ड
    0.72
     subsection
    0.71
    arima
    0.71
     deductions
    0.71
     bylaws
    0.71
    Activations Density 0.704%

    No Known Activations