© 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. 250735
    Prev
    Next
    INDEX
    Explanations

    ideal manufacturerProtestantism shortage stations

    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
     -
    0.52
    form
    0.46
     ON
    0.46
    어도
    0.46
     \(
    0.45
     Nato
    0.42
     Edison
    0.42
    <unused60>
    0.41
     &
    0.41
     (%)
    0.41
    POSITIVE LOGITS
     በሚ
    0.53
    <unused2>
    0.51
     እነ
    0.48
     ሌሎች
    0.47
     উপস্থিত
    0.47
     มุม
    0.47
    URNIZOR
    0.46
     czynności
    0.46
     قاسمی
    0.45
    Benzoimidazol
    0.45
    Activations Density 0.002%

    No Known Activations