© 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. 238802
    Prev
    Next
    INDEX
    Explanations

    arranged barcode graphics

    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
     thuế
    0.47
     Güney
    0.47
    Ꮂ
    0.46
    اتے
    0.46
     જુ
    0.46
    鹃
    0.46
     நிதி
    0.46
     മാന
    0.46
     tới
    0.45
    ທີ
    0.45
    POSITIVE LOGITS
    jet
    0.50
    し
    0.50
     (
    0.47
    input
    0.46
     disregard
    0.45
     ,
    0.45
     system
    0.45
    itol
    0.44
    context
    0.44
    ’
    0.44
    Activations Density 0.000%

    No Known Activations