© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37999
    Prev
    Next
    INDEX
    Explanations

    calling, election, spot

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

    mandate, clause

    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
     ות
    0.50
     cosidd
    0.49
     چیزی
    0.47
     وتح
    0.46
     Tomorrow
    0.46
    ("<
    0.46
    Tomorrow
    0.46
    BackgroundTask
    0.46
     سنو
    0.45
    <0x10>
    0.45
    POSITIVE LOGITS
     adversaries
    0.54
     obeyed
    0.50
    swell
    0.50
    mes
    0.49
     accredited
    0.49
     inflamed
    0.48
     impass
    0.48
     antimony
    0.48
     themselves
    0.47
    ла
    0.46
    Activations Density 0.001%

    No Known Activations