© 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. 41764
    Prev
    Next
    INDEX
    Explanations

    much for

    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
     whatnot
    1.26
    on
    1.23
    ure
    1.14
    ark
    1.11
    ama
    1.07
     frankly
    1.06
    ন
    1.05
    om
    1.04
    ch
    1.00
     from
    0.98
    POSITIVE LOGITS
    ت
    1.57
    ير
    1.46
    യ
    1.40
    ти
    1.36
    మ్‌
    1.36
     Sadh
    1.36
    𝓂
    1.35
    ือ
    1.34
    ྥ
    1.33
     iguales
    1.31
    Activations Density 0.000%

    No Known Activations