© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2120
    Prev
    Next
    INDEX
    Explanations

    pronouns and surrounding punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    踰
    0.39
     tocó
    0.38
    хара
    0.38
     quốc
    0.38
    사의
    0.37
    ﾋ
    0.37
     xác
    0.36
    ুপ
    0.35
    冎
    0.35
    φος
    0.35
    POSITIVE LOGITS
     it
    0.62
    它可以
    0.59
     It
    0.58
     Suitable
    0.57
    它
    0.56
     simply
    0.54
    同时也
    0.52
     meanwhile
    0.52
     它
    0.52
     moreover
    0.51
    Activations Density 0.000%

    No Known Activations