© 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. 92349
    Prev
    Next
    INDEX
    Explanations

    Ph.D. thesis

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

    algorithm definition or description

    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
    encio
    0.53
     مشرقی
    0.48
     &/
    0.47
     Oost
    0.46
     trov
    0.45
     olefins
    0.45
     Caribe
    0.45
     revest
    0.44
     Reth
    0.44
     secession
    0.44
    POSITIVE LOGITS
    ∗
    0.60
     dynamical
    0.53
     ∗
    0.52
    arXiv
    0.52
     arXiv
    0.51
    Computational
    0.51
     bijection
    0.50
    dynamical
    0.50
    Denote
    0.49
    ⋆
    0.49
    Activations Density 0.019%

    No Known Activations