© 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. 8774
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors

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

    sentence terminators followed by conjunctions

    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
     nitrile
    0.48
     samoglas
    0.44
    끅
    0.42
     geospatial
    0.42
    뇰
    0.41
    ጲ
    0.41
     espresso
    0.41
    Benzoimidazol
    0.40
     bushings
    0.40
    웡
    0.40
    POSITIVE LOGITS
     Поэтому
    0.54
     ಆದ್ದರಿಂದ
    0.52
    இது
    0.51
     නමුත්
    0.49
     இதனால்
    0.49
     இது
    0.48
     जिससे
    0.48
     ஆனால்
    0.47
     Moreover
    0.46
     Nhưng
    0.46
    Activations Density 0.088%

    No Known Activations