© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153459
    Prev
    Next
    INDEX
    Explanations

    want to

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

    tradition and spectacle

    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
     экране
    0.48
     lekker
    0.48
    ্যান
    0.45
     സ്ഥി
    0.45
     Sanchez
    0.44
    fiere
    0.44
    pele
    0.43
    𝐜
    0.43
    pple
    0.42
    াতাড়ি
    0.42
    POSITIVE LOGITS
    키
    0.45
    ﮭ
    0.45
    处于
    0.43
     åt
    0.42
    岂
    0.42
     '*':
    0.42
     đạo
    0.40
     nonEmpty
    0.40
     '%
    0.40
     inex
    0.40
    Activations Density 0.000%

    No Known Activations