© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56993
    Prev
    Next
    INDEX
    Explanations

    close-up of

    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
     Esports
    0.48
    ަ
    0.46
     网络
    0.45
     অনুমোদন
    0.42
     sociais
    0.41
     স্ট্যান্ডার্ড
    0.41
     Identities
    0.41
     reimag
    0.41
     famously
    0.41
     خودم
    0.40
    POSITIVE LOGITS
     पत्तियों
    0.46
    鈷
    0.46
    ruč
    0.45
    estomac
    0.43
     வயிற்றில்
    0.42
     dredge
    0.41
     vicinity
    0.41
    เกี่ยวกับ
    0.40
     अथवा
    0.39
    碰到
    0.39
    Activations Density 0.006%

    No Known Activations