© 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. 63766
    Prev
    Next
    INDEX
    Explanations

    places for accommodation or people

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

    C++ iostream include

    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
    мость
    0.49
     சிர
    0.49
     玄
    0.49
    ರ್ಧ
    0.49
    árez
    0.47
     ஹைட்
    0.47
    tuvo
    0.47
    Databaze
    0.46
     haberse
    0.46
     irrever
    0.46
    POSITIVE LOGITS
     rooms
    0.57
     C
    0.48
     Children
    0.47
     Rooms
    0.46
     комнаты
    0.46
     clockwise
    0.43
    x
    0.42
     people
    0.42
     Carolina
    0.42
    编制
    0.42
    Activations Density 0.000%

    No Known Activations