© 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. 13142
    Prev
    Next
    INDEX
    Explanations

    precepts, cultivate, HEAD, Art

    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
    졔
    0.80
    ♰
    0.78
    êt
    0.74
     Trou
    0.72
    𝘀
    0.72
     Boil
    0.71
    ер
    0.69
    gies
    0.69
    NBR
    0.69
    BES
    0.68
    POSITIVE LOGITS
    ान
    0.82
    很多
    0.79
     internationaux
    0.76
     quiser
    0.75
    ु
    0.75
    働
    0.75
    吗
    0.75
     workings
    0.74
    려면
    0.73
     dihasilkan
    0.73
    Activations Density 0.001%

    No Known Activations