© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1531
    Prev
    Next
    INDEX
    Explanations

    starts of journal titles

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

    journal citations or academic articles

    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
     morceau
    0.44
     ongles
    0.41
     層
    0.40
     polypes
    0.40
     tâche
    0.39
     baju
    0.38
     morceaux
    0.38
     mâles
    0.37
     quantidades
    0.37
     fistule
    0.37
    POSITIVE LOGITS
     International
    0.52
     J
    0.49
     Journal
    0.48
     Institute
    0.47
     University
    0.46
     A
    0.45
     K
    0.42
     World
    0.42
     Pacific
    0.42
     E
    0.41
    Activations Density 0.061%

    No Known Activations