© 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. 123501
    Prev
    Next
    INDEX
    Explanations

    links and citations

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

    X, Y coordinates

    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
    !\!\
    0.50
    てください
    0.44
    ;
    0.44
    ai
    0.43
    nless
    0.42
    !
    0.42
    hets
    0.41
    lite
    0.41
    atomic
    0.40
    স্বরূপ
    0.40
    POSITIVE LOGITS
     milioane
    0.54
    <unused1864>
    0.50
    ления
    0.49
     Mapa
    0.49
     Republicans
    0.48
     valores
    0.48
     restaurante
    0.47
     কণ্
    0.47
     persoane
    0.47
     அறிந்து
    0.47
    Activations Density 0.001%

    No Known Activations