© 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. 243702
    Prev
    Next
    INDEX
    Explanations

    margins, third, class, filling, thrift, quiescent, source

    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
     Вайлдберриз
    0.49
    вия
    0.47
    秋
    0.46
    гене
    0.44
    버
    0.43
    йн
    0.42
     акции
    0.42
    гает
    0.41
    нете
    0.40
    ках
    0.40
    POSITIVE LOGITS
     आफ्
    0.44
    মিল
    0.44
    鏻
    0.44
     canceling
    0.44
     família
    0.44
     Administración
    0.44
     معی
    0.44
    滖
    0.44
     Søren
    0.43
     Paren
    0.43
    Activations Density 0.000%

    No Known Activations