© 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. 67839
    Prev
    Next
    INDEX
    Explanations

    indicates relations

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

    male, M3GAN, usernames, last

    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
     vesicle
    0.42
    ।
    0.40
     dne
    0.40
     bisogna
    0.40
    ۔
    0.40
    día
    0.39
    iapan
    0.38
    they
    0.37
    ",[],"
    0.37
     saper
    0.37
    POSITIVE LOGITS
     demonstrates
    0.55
     illustrates
    0.54
     precludes
    0.50
     indicates
    0.49
     mortgage
    0.48
     परियोजनाओं
    0.47
     lenders
    0.46
     позволяет
    0.46
    Loans
    0.45
     shows
    0.45
    Activations Density 0.002%

    No Known Activations