© 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. 16973
    Prev
    Next
    INDEX
    Explanations

    attributed statements

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

    direct quotes and speech attribution

    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
    可以使用
    0.56
    需要
    0.39
    它可以
    0.39
    利用
    0.39
    可以将
    0.38
    不需要
    0.38
     workmanship
    0.38
    獲
    0.38
    %,
    0.38
     Hermitian
    0.38
    POSITIVE LOGITS
     says
    0.96
     säger
    0.88
    says
    0.85
     powiedział
    0.80
     라고
    0.79
     сказал
    0.78
     يقول
    0.76
    说道
    0.75
     mówi
    0.75
     said
    0.74
    Activations Density 0.060%

    No Known Activations