© 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. 44389
    Prev
    Next
    INDEX
    Explanations

    Here's a guide

    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
    !!!!
    0.26
    !!!
    0.26
     Hundreds
    0.25
    ?!
    0.25
    ;
    0.25
    ؟
    0.25
    ↵
    0.24
    );
    0.24
    ↵↵
    0.24
     dozens
    0.23
    POSITIVE LOGITS
    同时也
    0.27
     ankaŭ
    0.26
    ിലും
    0.25
     інших
    0.24
     கைப்ப
    0.24
     আসুন
    0.24
    Additionally
    0.24
     deff
    0.24
    atiable
    0.23
    erti
    0.23
    Activations Density 0.066%

    No Known Activations