© 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-262K
    7. 76002
    Prev
    Next
    INDEX
    Explanations

    there now…

    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_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
    鵠
    0.43
    ﻬ
    0.42
    ी
    0.41
    efois
    0.40
    聲
    0.40
     parameterType
    0.39
    GO
    0.39
    地下
    0.39
    ewhere
    0.38
     પાણી
    0.38
    POSITIVE LOGITS
     Joko
    0.45
     മികച്ച
    0.44
     Tracking
    0.43
    <0x0D>
    0.43
     uptick
    0.42
     CDC
    0.42
     USAID
    0.42
     sveik
    0.41
     d
    0.41
     FX
    0.41
    Activations Density 0.006%

    No Known Activations