© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7089
    Prev
    Next
    INDEX
    Explanations

    location and amenities

    np_acts-logits-general · gemini-2.5-flash-lite

    restaurants and dining locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的标准
    0.18
     stainless
    0.17
     nineteen
    0.16
     Ultraviolet
    0.16
    쥴
    0.16
     guér
    0.16
     carpets
    0.16
     Heute
    0.16
     Gründung
    0.16
    标准
    0.15
    POSITIVE LOGITS
     עם
    0.21
    lots
    0.20
    opportunities
    0.20
    姏
    0.19
    nice
    0.19
     Allows
    0.18
     позволя
    0.18
    lef
    0.18
    也很
    0.18
    導致
    0.17
    Activations Density 0.174%

    No Known Activations