© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55400
    Prev
    Next
    INDEX
    Explanations

    research and investigation

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

    urbanentire Earthwhy you

    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
    бор
    0.51
    正常
    0.46
    чика
    0.46
    枻
    0.45
    亨
    0.45
     пункта
    0.44
    ANDEZ
    0.44
    hout
    0.43
    뷔
    0.42
    玩法
    0.42
    POSITIVE LOGITS
     Siles
    0.57
     J
    0.54
     investigación
    0.52
     Sarah
    0.51
     research
    0.50
     araşt
    0.50
     Ö
    0.48
     bis
    0.48
     Alto
    0.48
     działania
    0.48
    Activations Density 0.000%

    No Known Activations