© 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. 49659
    Prev
    Next
    INDEX
    Explanations

    between words or phrases

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

    showing examples how it works

    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
    给
    0.48
    哪里
    0.44
    无
    0.44
     promoted
    0.42
    注明
    0.42
    (
    0.42
    ার্টমেন্ট
    0.42
     paranoid
    0.41
     hostess
    0.41
    包括
    0.41
    POSITIVE LOGITS
     giữa
    0.52
     இருக்கலாம்
    0.51
     عام
    0.50
     بین
    0.50
     県
    0.50
     życie
    0.49
     éché
    0.49
    between
    0.49
     TL
    0.48
     အတွ
    0.48
    Activations Density 0.000%

    No Known Activations