© 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. 13951
    Prev
    Next
    INDEX
    Explanations

    matching and pairing

    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
     emanating
    0.47
     over
    0.47
     thats
    0.46
     sprang
    0.45
    (
    0.45
    tree
    0.44
     auteur
    0.43
    [
    0.43
     над
    0.43
    मार्ग
    0.42
    POSITIVE LOGITS
     ਦਵਾਈ
    0.50
    <unused58>
    0.49
    ಿಕೊಂಡ
    0.46
     컬러
    0.46
     ஐந்து
    0.46
    ALAR
    0.46
     이름
    0.45
     Items
    0.45
     मैट
    0.45
    enderita
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.