© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35414
    Prev
    Next
    INDEX
    Explanations

    designing performance

    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
     anderer
    1.64
    澍
    1.48
    ية
    1.47
    unread
    1.43
     idiom
    1.41
    ድግዳ
    1.38
    ंशिक
    1.37
     Möglichkeiten
    1.34
    HAS
    1.32
     phenolic
    1.31
    POSITIVE LOGITS
     а
    1.55
    ли
    1.53
    ми
    1.48
    。
    1.41
    가
    1.32
    ন
    1.31
    ，
    1.28
    č
    1.28
    cheerful
    1.25
    ни
    1.23
    Activations Density 0.000%

    No Known Activations