© 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. 17410
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation

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

    joke punctuation followed by laughter

    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
    we
    0.41
     pagal
    0.40
     also
    0.39
    enjoy
    0.39
     prefer
    0.38
    用
    0.38
     també
    0.38
    group
    0.38
    Therefore
    0.37
    निवास
    0.37
    POSITIVE LOGITS
     ибо
    0.45
     కో
    0.42
    绶
    0.42
    额外
    0.41
     অভাবে
    0.41
     ليس
    0.41
     বিলম্ব
    0.41
     subTest
    0.40
    olutamente
    0.40
     মারাত্মক
    0.40
    Activations Density 0.001%

    No Known Activations