© 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. 9849
    Prev
    Next
    INDEX
    Explanations

    vitamins followed by a letter

    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
    ج
    1.84
    認為
    1.83
    馗
    1.79
     iż
    1.59
     harboring
    1.52
    هَا
    1.51
    ución
    1.49
    ーク
    1.48
    ро
    1.48
     Ня
    1.48
    POSITIVE LOGITS
    ar
    2.50
    TA
    1.87
    arı
    1.80
    ica
    1.65
    ER
    1.63
     hii
    1.63
    r
    1.61
    льше
    1.58
    lık
    1.55
    ್ಯ
    1.54
    Activations Density 0.005%

    No Known Activations