© 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. 11298
    Prev
    Next
    INDEX
    Explanations

    most efficient / substantial

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

    multiple, movies, Dramatic, communication, chances, BL

    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
     berkembang
    0.54
     ak
    0.51
     청
    0.49
     τὸν
    0.48
     yaş
    0.48
     kece
    0.48
     yaşı
    0.47
     공부
    0.47
     kişi
    0.46
     ა
    0.46
    POSITIVE LOGITS
    ারের
    0.54
    呈
    0.46
    ьогодні
    0.46
    CSF
    0.46
    hình
    0.45
    Shape
    0.45
    ήθ
    0.44
    df
    0.43
    minipage
    0.43
    Folding
    0.43
    Activations Density 0.000%

    No Known Activations