© 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. 63938
    Prev
    Next
    INDEX
    Explanations

    first followed by a noun

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

    drawings and diagrams

    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
     એલ
    0.51
    zeczy
    0.49
     européens
    0.44
     ভোক্ত
    0.44
    튿
    0.43
     proiz
    0.43
     সচিব
    0.43
     fréquence
    0.43
     influent
    0.43
     lập
    0.42
    POSITIVE LOGITS
    on
    0.54
    GH
    0.52
    draw
    0.50
    a
    0.50
    Draw
    0.49
    au
    0.49
    n
    0.49
    atti
    0.48
    String
    0.48
    nH
    0.48
    Activations Density 0.001%

    No Known Activations