© 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. 90839
    Prev
    Next
    INDEX
    Explanations

    vary the

    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
    жени
    0.44
     Украина
    0.42
    эм
    0.42
    (
    0.42
     surgeon
    0.41
    }=(\
    0.41
    겐
    0.41
    ukuran
    0.41
    間
    0.41
    ху
    0.39
    POSITIVE LOGITS
     geschikt
    0.49
     récomp
    0.48
     potenz
    0.47
    媲
    0.47
     farklı
    0.47
     الأساس
    0.46
     זה
    0.46
     διαφορε
    0.45
    适合
    0.44
     इसी
    0.43
    Activations Density 0.006%

    No Known Activations