© 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. 31922
    Prev
    Next
    INDEX
    Explanations

    He

    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
    ין
    2.20
    ের
    2.08
    sas
    1.95
    s
    1.95
    ів
    1.92
    ない
    1.86
    يها
    1.84
    sia
    1.77
    ियों
    1.77
    sala
    1.74
    POSITIVE LOGITS
     ومع
    1.53
     congruent
    1.48
    ত্বের
    1.47
     cứ
    1.45
    ور
    1.42
     t
    1.40
    comes
    1.40
    なる
    1.34
    끔
    1.33
    ថា
    1.31
    Activations Density 0.024%

    No Known Activations