© 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. 78139
    Prev
    Next
    INDEX
    Explanations

    giving or receiving something practical

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

    explaining purpose or result

    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
    on
    0.45
    stackrel
    0.42
    Resizable
    0.40
    about
    0.40
     অক্টোবর
    0.39
    ₀
    0.39
    📐
    0.39
    available
    0.38
     שני
    0.38
     GeoNames
    0.38
    POSITIVE LOGITS
     wickedness
    0.48
    代谢
    0.48
    痉
    0.48
     dakkh
    0.47
     meningitis
    0.46
     துன்ப
    0.44
     médical
    0.44
    烦
    0.44
     murderous
    0.44
     জটিল
    0.43
    Activations Density 0.002%

    No Known Activations