© 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. 151531
    Prev
    Next
    INDEX
    Explanations

    always effort

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

    comparing to bulk

    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
    aj
    0.58
    ри
    0.51
     हाइट
    0.49
    逮捕
    0.49
    зни
    0.48
     автоматы
    0.48
    ب
    0.48
    উর
    0.47
    どんな
    0.47
    閉店
    0.47
    POSITIVE LOGITS
     strategy
    0.48
     understandable
    0.46
     voiced
    0.46
     Ministerial
    0.46
     tradisional
    0.45
     inextricably
    0.45
     IntPtr
    0.45
     rethinking
    0.44
     Förder
    0.44
     Verständnis
    0.44
    Activations Density 0.001%

    No Known Activations