© 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. 40594
    Prev
    Next
    INDEX
    Explanations

    time spans

    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
    א
    1.38
    ९
    1.38
     unjust
    1.34
    aría
    1.30
     thở
    1.28
     súa
    1.28
     ТО
    1.23
    рого
    1.23
    Однако
    1.20
    ᠮ
    1.20
    POSITIVE LOGITS
    s
    1.71
    st
    1.28
    ات
    1.28
    w
    1.23
    ુ
    1.16
     Breaks
    1.14
    l
    1.10
    .
    1.10
    notice
    1.09
     sebelumnya
    1.09
    Activations Density 0.000%

    No Known Activations