© 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. 247819
    Prev
    Next
    INDEX
    Explanations

    society, someone, sold, Instant, two

    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
    嗤
    0.43
    จะต้อง
    0.42
     आचार्य
    0.42
    gutter
    0.41
     बाब
    0.41
     oppon
    0.41
     אנ
    0.41
    בי
    0.41
     extreme
    0.41
    iskt
    0.41
    POSITIVE LOGITS
     décès
    0.50
     Yankees
    0.47
     nacionales
    0.46
     Tories
    0.46
    ".[
    0.46
     mà
    0.46
     salariés
    0.45
     élargies
    0.45
     Locally
    0.44
     Grows
    0.44
    Activations Density 0.000%

    No Known Activations