© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10537
    Prev
    Next
    INDEX
    Explanations

    infrastructure and its parts

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

    infrastructure and cities

    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
    小时候
    0.58
     Änderung
    0.57
     фаразы
    0.57
     Calyce
    0.55
     Při
    0.55
    ریشن
    0.54
     Anfrage
    0.54
    烦
    0.54
    菈
    0.54
     عنہ
    0.53
    POSITIVE LOGITS
     hospitals
    0.79
     refineries
    0.77
     infrastructure
    0.75
     infrastructures
    0.73
    infrastructure
    0.70
     infraestructura
    0.68
     airports
    0.68
     infrastrukt
    0.68
    facilities
    0.68
     инфраструк
    0.68
    Activations Density 0.085%

    No Known Activations