© 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. 171817
    Prev
    Next
    INDEX
    Explanations

    game or competitive

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

    find things

    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
    m
    0.60
    sal
    0.59
    nft
    0.54
    f
    0.54
    tay
    0.52
    ks
    0.50
    ca
    0.50
    fia
    0.50
    ar
    0.49
    ch
    0.48
    POSITIVE LOGITS
     bordo
    0.54
     hòa
    0.51
     querying
    0.48
     тим
    0.47
    ია
    0.47
     interrogation
    0.46
     треба
    0.45
     cheerleader
    0.45
     ។
    0.45
    他們的
    0.45
    Activations Density 0.001%

    No Known Activations