© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78025
    Prev
    Next
    INDEX
    Explanations

    market factors and analysis

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

    non-latin characters

    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
    Negative Logits
    nost
    0.57
    peter
    0.52
    nos
    0.49
     ardent
    0.49
    o
    0.48
    minister
    0.48
     konstruk
    0.47
    veled
    0.47
    name
    0.46
    smouth
    0.46
    POSITIVE LOGITS
    нь
    0.50
    짭
    0.46
    팔
    0.46
     JUD
    0.45
    дук
    0.44
     môi
    0.44
    鋆
    0.44
     PLANT
    0.44
    훅
    0.44
    햅
    0.43
    Activations Density 0.001%

    No Known Activations