© 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. 13442
    Prev
    Next
    INDEX
    Explanations

    combining abstract things, ideas, or concepts

    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
    og
    1.98
    い
    1.98
    ong
    1.92
    od
    1.89
    la
    1.89
    િ
    1.89
    end
    1.79
    א
    1.79
    ell
    1.74
    יל
    1.73
    POSITIVE LOGITS
    ی
    2.36
     следует
    1.80
    𝐀
    1.77
    ੳ
    1.66
    ायत
    1.62
     ALLOYS
    1.60
     endere
    1.60
     дзяржа
    1.60
     olvides
    1.60
     Consultez
    1.59
    Activations Density 0.041%

    No Known Activations