© 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. 92446
    Prev
    Next
    INDEX
    Explanations

    owner, indemnifiy, right

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

    Alerts / living costs

    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
     اثنين
    0.53
     Пе
    0.50
    を持っている
    0.49
     м
    0.49
     snap
    0.49
    кот
    0.48
    б
    0.47
     обо
    0.46
     bouts
    0.46
    вые
    0.46
    POSITIVE LOGITS
     satisfacción
    0.44
     gunung
    0.42
    ’
    0.41
    IER
    0.40
    INDER
    0.39
     সমাধি
    0.39
     salón
    0.39
    ஜ்மஹ
    0.38
    beginner
    0.38
     کارکن
    0.38
    Activations Density 0.001%

    No Known Activations