© 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. 75847
    Prev
    Next
    INDEX
    Explanations

    new version, new sofa

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

    80/20 principle

    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
    Negative Logits
    #,
    0.45
    w
    0.44
    unk
    0.42
    ses
    0.41
    IN
    0.41
    ̓
    0.41
    mck
    0.39
    selt
    0.38
    hydroxy
    0.38
    ne
    0.38
    POSITIVE LOGITS
     可能
    0.50
     mostrar
    0.50
    اقة
    0.49
     Бо
    0.47
    жие
    0.47
     排
    0.47
    Measure
    0.47
     coral
    0.46
     バ
    0.46
     人気
    0.46
    Activations Density 0.000%

    No Known Activations