© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8027
    Prev
    Next
    INDEX
    Explanations

    function and define

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
     conceptions
    0.40
    摀
    0.38
     contradict
    0.36
     uneasy
    0.35
     conception
    0.35
     conceive
    0.34
    दी
    0.34
     hiss
    0.34
     disruptive
    0.34
     superficies
    0.33
    POSITIVE LOGITS
    ionicons
    0.46
    न्होंने
    0.40
    scrollTo
    0.40
     чыныгы
    0.40
    serif
    0.39
    ლებელია
    0.39
     }^{*}$
    0.39
    logo
    0.39
     स्पून
    0.39
    addr
    0.38
    Activations Density 0.052%

    No Known Activations