© 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. 10066
    Prev
    Next
    INDEX
    Explanations

    folk song genre

    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
    нд
    2.03
    ש
    1.88
    ті
    1.75
    ست
    1.71
    ু
    1.66
    dır
    1.63
    ör
    1.57
    ats
    1.56
    やつ
    1.55
    езде
    1.53
    POSITIVE LOGITS
    ۵
    2.08
    ۴
    1.99
    निमल
    1.86
    idene
    1.82
     cercanas
    1.77
    kfollowers
    1.77
    枼
    1.77
     humanidad
    1.72
    ంశ
    1.70
     Некоторые
    1.70
    Activations Density 0.004%

    No Known Activations