© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12045
    Prev
    Next
    INDEX
    Explanations

    classification and multi-lingual labels

    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_40_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
    вок
    0.43
    дой
    0.41
     seep
    0.41
     plung
    0.40
     embarrass
    0.39
     swivel
    0.39
     inbox
    0.39
    送
    0.38
    coin
    0.38
     interchanges
    0.38
    POSITIVE LOGITS
     ഗവേഷ
    0.52
     શિક્ષણ
    0.46
     بیشتر
    0.45
    ㈤
    0.44
     المزيد
    0.42
     ರಚ
    0.41
     तंत्र
    0.41
     এসএসসি
    0.40
     Giáo
    0.40
     ተጨማሪ
    0.40
    Activations Density 0.001%

    No Known Activations