© 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. 139727
    Prev
    Next
    INDEX
    Explanations

    other; ability; plan

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

    seeking advice about actions

    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
     a
    0.63
     new
    0.58
     comes
    0.55
    begin
    0.54
     begins
    0.54
    0.54
     your
    0.53
     you
    0.52
     meet
    0.52
     is
    0.51
    POSITIVE LOGITS
    所以我
    0.55
     поэтому
    0.55
     философ
    0.55
     пыта
    0.52
    黜
    0.52
    ையால்
    0.52
    并通过
    0.52
    所以在
    0.51
    autoarima
    0.50
    贖
    0.50
    Activations Density 0.002%

    No Known Activations