© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239840
    Prev
    Next
    INDEX
    Explanations

    names followed by verbs

    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
    Negative Logits
     nedeniyle
    0.46
    意味
    0.46
     tanpa
    0.45
     கண்டுபிடிக்க
    0.45
    可能性
    0.43
    ⇐
    0.43
     ইস
    0.42
     அவ
    0.42
    Products
    0.41
     محصولات
    0.41
    POSITIVE LOGITS
     담
    0.45
    িন্দা
    0.44
    何况
    0.43
     prayed
    0.42
     addNew
    0.42
     ozbil
    0.42
    il
    0.42
    itakan
    0.42
    었다
    0.42
     enjo
    0.42
    Activations Density 0.000%

    No Known Activations