© 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. 9692
    Prev
    Next
    INDEX
    Explanations

    visible on page

    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
    د
    2.44
    t
    2.39
    ה
    2.38
    d
    2.28
    ی
    2.20
    ت
    2.16
    ку
    2.03
    ных
    2.02
    га
    2.00
    ő
    1.95
    POSITIVE LOGITS
     👀
    1.89
     anthropologist
    1.71
     passivation
    1.61
     וב
    1.59
     mammoth
    1.58
     ظل
    1.57
     seder
    1.56
     Debi
    1.55
     sorti
    1.54
     lumps
    1.54
    Activations Density 0.061%

    No Known Activations