© 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. 10053
    Prev
    Next
    INDEX
    Explanations

    cursor, castle, Costco, MST

    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
    ну
    2.34
    ાન
    2.23
    ot
    2.22
    𝚜
    2.08
    𝘨
    2.03
    ook
    1.99
    是在
    1.99
    લ
    1.95
    ्य
    1.94
    са
    1.88
    POSITIVE LOGITS
    א
    2.86
    ل
    2.47
    ட
    2.44
    ش
    2.31
    。
    2.25
    ك
    2.14
    ना
    2.13
    ções
    2.08
    わたし
    2.05
    و
    1.98
    Activations Density 0.119%

    No Known Activations