© 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-16K
    7. 12869
    Prev
    Next
    INDEX
    Explanations

    introduces additional information

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

    parenthetical phrases and 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_16k_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
    Therefore
    0.77
    Якщо
    0.64
    Однако
    0.63
     Поэтому
    0.60
    However
    0.58
    После
    0.57
     Therefore
    0.56
    *.
    0.56
     поэтому
    0.55
     Конечно
    0.55
    POSITIVE LOGITS
     whose
    0.67
     cui
    0.55
     presumably
    0.55
     which
    0.53
     consisting
    0.53
     comprising
    0.51
     lanthan
    0.50
     whom
    0.49
     cuya
    0.49
     deemed
    0.48
    Activations Density 0.182%

    No Known Activations