© 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. 9470
    Prev
    Next
    INDEX
    Explanations

    words ending 'ly'

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

    adverbs ending in ly or ably

    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
     metagen
    0.47
    ਰ
    0.46
    ल
    0.44
    ᔾ
    0.43
     binh
    0.43
     Messages
    0.43
     Ekonomi
    0.43
     interstitials
    0.43
    वण
    0.42
    іга
    0.41
    POSITIVE LOGITS
    y
    0.51
     كأس
    0.45
    achron
    0.45
    review
    0.44
     пыта
    0.44
    ey
    0.44
     مشغول
    0.44
    ุปกรณ์
    0.43
    weds
    0.42
    diagn
    0.42
    Activations Density 0.002%

    No Known Activations