© 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. 243064
    Prev
    Next
    INDEX
    Explanations

    adverbs and specific word followers

    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
     คือ
    0.47
     Президента
    0.47
    ORIENT
    0.47
     Воло
    0.46
     Италия
    0.46
     Мы
    0.45
    =(\
    0.45
     المشروع
    0.45
     Про
    0.44
    sugar
    0.44
    POSITIVE LOGITS
    stelle
    0.60
    рен
    0.50
    ότη
    0.49
     studi
    0.49
    εύ
    0.47
    λή
    0.46
     deinen
    0.46
     ἀ
    0.46
    쐞
    0.46
    ра
    0.44
    Activations Density 0.000%

    No Known Activations