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

    Neuronpedia

    Jacobian LensNEW
    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. 2655
    Prev
    Next
    INDEX
    Explanations

    ugly descriptions

    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
    ال
    2.20
    ی
    2.03
    ك
    2.00
    ى
    1.90
    很多
    1.75
    あります
    1.74
    یف
    1.73
    েই
    1.63
    ה
    1.62
    ıyla
    1.59
    POSITIVE LOGITS
    re
    1.75
     rhenium
    1.71
    ä
    1.55
    ר
    1.55
     surprise
    1.51
     secretion
    1.51
    LIN
    1.51
     sarcoma
    1.51
     warts
    1.48
     sediment
    1.46
    Activations Density 0.008%

    No Known Activations