© 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-262K
    7. 3747
    Prev
    Next
    INDEX
    Explanations

    age ranges

    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_262k_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
    ter
    1.16
    ssa
    1.09
    ร
    1.07
    ten
    1.03
    rep
    1.02
    ri
    1.02
    ron
    1.02
    ng
    1.00
    most
    1.00
    radical
    0.97
    POSITIVE LOGITS
    ית
    1.29
    يل
    1.28
    ぇ
    1.28
    ш
    1.27
    ﺮ
    1.27
    ность
    1.25
    க்கூடிய
    1.22
    ილი
    1.21
    ان
    1.20
    eer
    1.20
    Activations Density 0.017%

    No Known Activations