© 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. 91051
    Prev
    Next
    INDEX
    Explanations

    geographical locations

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

    contextual appropriateness

    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
    C
    0.49
    って
    0.48
    D
    0.48
    SCC
    0.47
    ის
    0.46
    N
    0.46
    Д
    0.45
    С
    0.45
     உங்களுக்கு
    0.45
    というのは
    0.45
    POSITIVE LOGITS
     événement
    0.56
     nổi
    0.51
     edificios
    0.50
     Offices
    0.49
     investir
    0.48
     investasi
    0.48
     partenariat
    0.48
     implique
    0.48
     zainteres
    0.46
     accueille
    0.46
    Activations Density 0.000%

    No Known Activations