© 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. 75352
    Prev
    Next
    INDEX
    Explanations

    list separators or modifiers

    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
     După
    0.56
    ató
    0.46
     deoarece
    0.46
    ostęp
    0.46
    ).
    0.45
     remport
    0.45
     ị
    0.45
     Gä
    0.45
     wundersch
    0.44
    ഭം
    0.44
    POSITIVE LOGITS
    把
    0.43
     познакоми
    0.41
     corrector
    0.41
     타이
    0.40
    或
    0.39
     anecdote
    0.39
     delimiter
    0.39
     кни
    0.38
     calendar
    0.38
     spurt
    0.38
    Activations Density 0.008%

    No Known Activations