© 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. 69257
    Prev
    Next
    INDEX
    Explanations

    Englishness

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

    Airbnb, seed funding, personalization

    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
     infrastructure
    0.65
     Infrastructure
    0.60
     nutrition
    0.54
     Energy
    0.54
     H
    0.52
     University
    0.52
     Infrast
    0.52
     appliances
    0.52
     infrast
    0.51
     education
    0.50
    POSITIVE LOGITS
     প্রমুখ
    0.51
    🛹
    0.50
    🛤
    0.50
    👘
    0.50
    🧖
    0.49
    νον
    0.49
    🏹
    0.49
     victoire
    0.48
    loé
    0.48
    🏄
    0.48
    Activations Density 0.001%

    No Known Activations