© 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. 136447
    Prev
    Next
    INDEX
    Explanations

    Gunicorn, € , flow, disqualification

    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
    㧿
    0.52
    퇸
    0.48
    iovascular
    0.47
    പം
    0.45
    ncoder
    0.45
    嬂
    0.45
     ჩვენ
    0.44
    nsen
    0.44
    repeated
    0.44
    ಕ್ತಿಯ
    0.43
    POSITIVE LOGITS
     sur
    0.46
     što
    0.46
     karar
    0.46
     que
    0.46
     surpr
    0.44
     firme
    0.44
     gás
    0.43
     j
    0.43
     ch
    0.43
     matriz
    0.43
    Activations Density 0.001%

    No Known Activations