© 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-16K
    7. 9617
    Prev
    Next
    INDEX
    Explanations

    pretty followed by adjective

    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_16k_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
    ется
    2.58
     dotycz
    2.28
    mış
    2.11
    ‌است
    2.03
    ಲ್ಲಿ
    1.99
     soát
    1.98
    我都
    1.93
    ﾟ
    1.92
    습니다
    1.91
    ्स
    1.90
    POSITIVE LOGITS
    ag
    2.38
    id
    2.19
    ed
    2.13
    व
    2.00
    ри
    1.91
    д
    1.91
    ich
    1.91
    or
    1.88
    ain
    1.87
    ac
    1.86
    Activations Density 0.009%

    No Known Activations