© 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. 75404
    Prev
    Next
    INDEX
    Explanations

    children, parents, and medicine

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

    scripting visuals

    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
    Nums
    0.43
    נם
    0.42
    귿
    0.41
    GOLD
    0.40
    吒
    0.39
    ⚙
    0.39
     керами
    0.39
    〠
    0.39
     হেঁ
    0.39
    🛖
    0.39
    POSITIVE LOGITS
     nouvel
    0.55
     child
    0.53
     következő
    0.53
     divor
    0.52
     medizin
    0.50
     والدین
    0.50
     prenant
    0.50
     procedimento
    0.50
     fiatal
    0.49
     kinderen
    0.49
    Activations Density 0.001%

    No Known Activations