© 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. 103523
    Prev
    Next
    INDEX
    Explanations

    unless otherwise, they must, they may

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

    pattern in lists

    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
    that
    0.63
    routes
    0.55
    concepts
    0.52
    goods
    0.51
    products
    0.49
    politics
    0.48
     comprehension
    0.48
    1
    0.48
    荘
    0.48
    picker
    0.47
    POSITIVE LOGITS
     maks
    0.46
     vise
    0.46
     Tesco
    0.45
     satin
    0.45
     CDMA
    0.44
     callus
    0.43
    年以上
    0.43
     lado
    0.42
     teal
    0.42
     mono
    0.42
    Activations Density 0.011%

    No Known Activations