© 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. 35767
    Prev
    Next
    INDEX
    Explanations

    theological discussions

    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
    ểm
    1.51
    ль
    1.44
    to
    1.39
     bầu
    1.39
     incor
    1.34
    彡
    1.33
    یف
    1.31
    蜒
    1.31
    ter
    1.30
    ޕ
    1.30
    POSITIVE LOGITS
    ä
    2.11
    ни
    2.06
    да
    1.91
    ار
    1.91
    ాలు
    1.82
    і
    1.80
    ره
    1.67
    au
    1.63
    ρα
    1.63
    ре
    1.62
    Activations Density 0.001%

    No Known Activations