© 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. 197527
    Prev
    Next
    INDEX
    Explanations

    publications that

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

    asking to inquire

    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
    ार
    0.55
    ी
    0.51
    bble
    0.51
    жите
    0.50
    ्याचा
    0.49
    ಿಯಾಗ
    0.48
     कोस
    0.48
    埂
    0.48
    AUGUST
    0.47
    чный
    0.47
    POSITIVE LOGITS
     né
    0.46
     لوی
    0.44
    ückt
    0.43
     şehir
    0.42
    ürm
    0.42
     completamente
    0.42
     الإ
    0.41
     ఎవరు
    0.41
     왼
    0.41
    Saver
    0.41
    Activations Density 0.001%

    No Known Activations