© 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. 29917
    Prev
    Next
    INDEX
    Explanations

    don't write, they'll transmit

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

    problem resolution actions

    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
    they
    0.48
    camore
    0.46
    Caroline
    0.46
    became
    0.46
    катери
    0.45
    с
    0.44
    appears
    0.44
    blit
    0.43
    emplo
    0.43
    ф
    0.42
    POSITIVE LOGITS
     soyez
    0.45
     ہے۔
    0.45
     gör
    0.44
     puh
    0.44
     discrim
    0.43
     sco
    0.43
     ď
    0.43
     lösen
    0.43
     ہوں۔
    0.42
     sind
    0.42
    Activations Density 0.000%

    No Known Activations