© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146574
    Prev
    Next
    INDEX
    Explanations

    locations impacted

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

    location

    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
     الدين
    0.82
     in
    0.72
    ائ
    0.66
    ذك
    0.64
    ئين
    0.64
    ح
    0.64
    ائي
    0.63
    يد
    0.61
    ركه
    0.61
    ٽ
    0.61
    POSITIVE LOGITS
     Location
    1.32
     getLocation
    1.28
     LOCATION
    1.27
    location
    1.26
     location
    1.24
     lokasi
    1.24
     Locations
    1.22
     locations
    1.17
    locations
    1.17
     위치
    1.09
    Activations Density 0.142%

    No Known Activations