© 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. 114249
    Prev
    Next
    INDEX
    Explanations

    Yet older, not distrust

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

    while, will, vulnerability

    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
    گ
    0.50
    factorial
    0.49
    deaths
    0.48
    再一次
    0.44
     rediscover
    0.44
    ん
    0.43
    machines
    0.43
    む
    0.42
     farmac
    0.42
    families
    0.42
    POSITIVE LOGITS
    oblasts
    0.49
     পাশে
    0.48
     выстав
    0.48
    পাশের
    0.44
     WENO
    0.44
     couldn
    0.43
    าว
    0.43
     wasn
    0.43
     เพื่อน
    0.42
     동작
    0.42
    Activations Density 0.001%

    No Known Activations