© 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. 19069
    Prev
    Next
    INDEX
    Explanations

    react dependencies and versions

    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
    apan
    0.40
     मानचित्र
    0.39
     copii
    0.39
     firefox
    0.39
    Gmail
    0.38
     suscrib
    0.37
    諷
    0.37
     사람들이
    0.37
    厛
    0.36
    ཎ
    0.36
    POSITIVE LOGITS
     ও
    0.44
     wrinkled
    0.41
     gemäß
    0.38
     toxin
    0.38
     inoculated
    0.38
     KOH
    0.38
     pigmentation
    0.37
    гії
    0.37
     thermoplastic
    0.37
     कैंडिडेट्स
    0.37
    Activations Density 0.001%

    No Known Activations