© 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. 104814
    Prev
    Next
    INDEX
    Explanations

    classical and academic knowledge

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

    AI insights and applications

    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
     bouton
    0.63
    뽁
    0.50
     buton
    0.49
     кнопку
    0.48
     кноп
    0.47
    arrage
    0.46
    繁殖
    0.46
     veut
    0.45
    駄
    0.45
    vata
    0.45
    POSITIVE LOGITS
     in
    0.50
     classical
    0.48
     memories
    0.46
     classics
    0.46
     academia
    0.45
     importance
    0.44
     understands
    0.44
     informatics
    0.43
     advise
    0.43
     advises
    0.43
    Activations Density 0.000%

    No Known Activations