© 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. 188185
    Prev
    Next
    INDEX
    Explanations

    audible alarm

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

    locations and actions

    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
     dito
    0.52
    清
    0.50
    gün
    0.50
    gı
    0.48
    classe
    0.46
    事務
    0.46
    isé
    0.45
    du
    0.44
    sho
    0.44
     facet
    0.44
    POSITIVE LOGITS
     коронави
    0.51
     KNeighbors
    0.51
    лет
    0.50
     оптими
    0.49
    猁
    0.48
     равномер
    0.48
     tcpHeader
    0.47
    堞
    0.47
    ㄼ
    0.47
    इस
    0.46
    Activations Density 0.000%

    No Known Activations