© 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. 49917
    Prev
    Next
    INDEX
    Explanations

    Netflix Original

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

    Turkey Sausage or Breast

    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
    t
    0.50
     الدوال
    0.48
     eminently
    0.47
     Zh
    0.45
    n
    0.45
     ដ
    0.44
    ोल
    0.43
     vulture
    0.43
     Dink
    0.43
    wh
    0.43
    POSITIVE LOGITS
     fortsatt
    0.47
     följande
    0.46
    স্ত
    0.46
     entendido
    0.45
     siguientes
    0.44
    baseURL
    0.42
     Posteriormente
    0.42
    朤
    0.41
     থাকিতে
    0.40
    itió
    0.40
    Activations Density 0.000%

    No Known Activations