© 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. 206065
    Prev
    Next
    INDEX
    Explanations

    search and find

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

    names and professions

    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
    important
    0.53
    ext
    0.52
    acceptable
    0.49
    expertise
    0.49
    exc
    0.48
    expect
    0.48
    ann
    0.48
    勢
    0.47
    ih
    0.47
    embedded
    0.47
    POSITIVE LOGITS
     Waren
    0.56
     accountant
    0.53
     carène
    0.52
     engra
    0.51
     pintor
    0.51
     Pedro
    0.50
     capitaine
    0.48
     Jésus
    0.48
     Soldaten
    0.48
     professora
    0.48
    Activations Density 0.001%

    No Known Activations