© 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. 41876
    Prev
    Next
    INDEX
    Explanations

    carefully followed by actions

    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
    螅
    1.38
    tól
    1.30
    dan
    1.30
    tl
    1.24
    ra
    1.21
    ted
    1.21
     Städ
    1.18
    tar
    1.14
     emphasis
    1.14
     emphasizing
    1.12
    POSITIVE LOGITS
    ن
    1.77
    و
    1.50
    নীর
    1.46
    ،
    1.41
    нию
    1.38
    ная
    1.34
     maneira
    1.34
     stronie
    1.33
    ਖ
    1.32
    веду
    1.30
    Activations Density 0.001%

    No Known Activations