© 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-65K
    7. 51370
    Prev
    Next
    INDEX
    Explanations

    multi-language and specific technical terms

    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_65k_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
     equipment
    0.38
     infrastructure
    0.38
     m
    0.38
     warehouses
    0.37
     systems
    0.37
     livestock
    0.36
     gases
    0.36
     housings
    0.35
    0.35
     gas
    0.34
    POSITIVE LOGITS
    เพื่อให้
    0.37
    antwoord
    0.37
    Ꭳ
    0.36
    ittää
    0.34
    밌
    0.34
     ჩატი
    0.34
    ée
    0.34
     подробно
    0.34
    为
    0.34
    řej
    0.34
    Activations Density 0.001%

    No Known Activations