© 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. 109636
    Prev
    Next
    INDEX
    Explanations

    distinct two-bar grille

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

    size or magnitude

    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
     هيا
    0.52
     zacz
    0.52
     просмо
    0.52
     المرك
    0.50
     vigueur
    0.50
     odbior
    0.50
     наиболее
    0.50
    埥
    0.50
     включая
    0.50
     dzien
    0.50
    POSITIVE LOGITS
    smith
    0.49
     Pen
    0.48
    n
    0.47
    p
    0.47
    !
    0.46
    ness
    0.46
     Market
    0.45
     retail
    0.44
     pen
    0.44
    spatial
    0.44
    Activations Density 0.001%

    No Known Activations