© 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. 8245
    Prev
    Next
    INDEX
    Explanations

    place names and street types

    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
     bytecode
    0.24
     serialization
    0.22
     मेटा
    0.22
     overwrite
    0.22
     chữ
    0.21
    {,}
    0.21
     dépl
    0.21
     آپ
    0.21
     normalize
    0.21
     retry
    0.21
    POSITIVE LOGITS
    ﾅ
    0.27
    6
    0.26
    হাট
    0.26
    وني
    0.25
    庐
    0.25
     parku
    0.25
    apolis
    0.25
    있
    0.24
    strasse
    0.24
     airport
    0.24
    Activations Density 0.028%

    No Known Activations