© 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. 218089
    Prev
    Next
    INDEX
    Explanations

    launching and scheduling events

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

    Championship Vinyl NBA

    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
     Donovan
    0.47
     conceptions
    0.47
    衔
    0.44
     assumption
    0.42
     Jodie
    0.42
     Downey
    0.42
     армии
    0.41
     বোপ
    0.41
    练
    0.41
     sleeved
    0.41
    POSITIVE LOGITS
    (
    0.58
    o
    0.53
    h
    0.52
    ूं
    0.52
    oo
    0.50
    l
    0.50
    I
    0.49
    azgo
    0.49
    ka
    0.49
    bou
    0.48
    Activations Density 0.001%

    No Known Activations