© 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. 190268
    Prev
    Next
    INDEX
    Explanations

    production, historically, jugs, neighbor

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

    world, science, finance, code

    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
    nogo
    0.51
     situ
    0.48
    Rt
    0.45
    v
    0.45
     generators
    0.44
    وسط
    0.44
    engines
    0.44
     Sito
    0.44
    Mb
    0.43
    ʿ
    0.43
    POSITIVE LOGITS
     экзем
    0.52
     няколко
    0.49
     нескольких
    0.47
    CurrentByte
    0.46
     снаб
    0.46
    нение
    0.45
    کنش
    0.44
    ಾದರೆ
    0.44
     చెర్రీ
    0.44
    лка
    0.43
    Activations Density 0.001%

    No Known Activations