© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7183
    Prev
    Next
    INDEX
    Explanations

    battery pack

    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
    ל
    1.87
    ิน
    1.86
    น
    1.71
    اد
    1.68
    ตรฐาน
    1.67
    ן
    1.59
    ان
    1.57
    ной
    1.57
    ాన్ని
    1.55
    ਾ
    1.54
    POSITIVE LOGITS
    う
    1.48
     Rho
    1.45
     Env
    1.39
    그러나
    1.35
    कुंठ
    1.34
    ς
    1.34
    comment
    1.27
    OTS
    1.24
     রকম
    1.23
    yyyyyyyy
    1.22
    Activations Density 0.004%

    No Known Activations