© 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. 91057
    Prev
    Next
    INDEX
    Explanations

    states and cities

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

    US 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
    Negative Logits
    ヴェ
    0.46
    ቖ
    0.46
    اب
    0.44
    छ
    0.44
    公路
    0.43
    曼
    0.43
    Пі
    0.43
    ALBERT
    0.43
    학생
    0.42
    쾰
    0.42
    POSITIVE LOGITS
     Minnesota
    0.67
     Maryland
    0.64
     Massachusetts
    0.64
     Illinois
    0.62
     Kentucky
    0.60
     Wisconsin
    0.60
     Maine
    0.60
     Missouri
    0.59
     Tennessee
    0.59
     Oregon
    0.59
    Activations Density 0.203%

    No Known Activations