© 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. 237545
    Prev
    Next
    INDEX
    Explanations

    preposition or plural pronoun

    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
    تميز
    0.57
     Siempre
    0.54
    بوط
    0.54
    洮
    0.54
     prodotti
    0.54
     llamada
    0.54
     Sempre
    0.52
    Siempre
    0.51
     subray
    0.51
    શિ
    0.50
    POSITIVE LOGITS
     editorials
    0.46
     Decoding
    0.45
     Kapitel
    0.43
     화면
    0.43
    getTitle
    0.43
     결
    0.42
     конференции
    0.42
     회
    0.41
     놓고
    0.41
    Totals
    0.41
    Activations Density 0.000%

    No Known Activations