© 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. 199348
    Prev
    Next
    INDEX
    Explanations

    eventual Airport

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

    questions asking "what" or "describe"

    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
    SizeType
    0.46
    陸
    0.42
     ਘ
    0.42
    <0x86>
    0.40
    льності
    0.39
    сцю
    0.39
    сць
    0.39
    σταν
    0.39
     মস্ক
    0.39
    率
    0.38
    POSITIVE LOGITS
     Lagu
    0.54
     disimpan
    0.48
     wither
    0.47
     buat
    0.46
    苚
    0.46
     Skyscrapers
    0.46
     menghasilkan
    0.45
     dimas
    0.45
    buat
    0.45
     paralel
    0.45
    Activations Density 0.001%

    No Known Activations