© 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. 253097
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    an
    0.56
     frat
    0.51
    植
    0.50
    actively
    0.49
    툭
    0.47
    a
    0.45
     cuadro
    0.45
     A
    0.44
     quadrant
    0.44
     FUTURE
    0.43
    POSITIVE LOGITS
    писы
    0.48
     वॉटर
    0.47
     ملین
    0.45
     წყ
    0.45
     هل
    0.44
     consom
    0.44
     фай
    0.43
     پذیر
    0.43
     зелены
    0.43
     formatDate
    0.43
    Activations Density 0.002%

    No Known Activations