© 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. 202572
    Prev
    Next
    INDEX
    Explanations

    after "the"

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

    questioning, doubt, or creativity

    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
    然后在
    0.50
     정의
    0.48
    。『
    0.46
    도
    0.46
    、『
    0.46
    سام
    0.45
    ี่
    0.45
     절대
    0.44
     assigning
    0.44
    ジタル
    0.43
    POSITIVE LOGITS
    endor
    0.55
    h
    0.52
    ul
    0.50
    cht
    0.48
     ضمان
    0.48
    ichter
    0.47
     tío
    0.47
    gor
    0.47
    ومي
    0.46
    nik
    0.46
    Activations Density 0.000%

    No Known Activations