© 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. 55438
    Prev
    Next
    INDEX
    Explanations

    appealing pair of sneakers

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

    order of operations

    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
    വി
    0.61
    Гу
    0.52
     Inggris
    0.51
     możli
    0.51
    辩
    0.51
     utwor
    0.50
    Př
    0.50
    อังกฤษ
    0.50
    苏
    0.50
    Aby
    0.50
    POSITIVE LOGITS
     bartenders
    0.55
     composting
    0.52
     subpoena
    0.50
     disgraced
    0.50
     Cadillac
    0.49
     cake
    0.49
     ceremony
    0.48
     cupcakes
    0.47
     candles
    0.47
     Camry
    0.47
    Activations Density 0.000%

    No Known Activations