© 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. 166656
    Prev
    Next
    INDEX
    Explanations

    where prohibited

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

    spectacles perched on nose

    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
    ႉ
    0.48
    aider
    0.46
    вший
    0.44
    кои
    0.44
    椅子
    0.43
    上面
    0.40
     estudo
    0.40
    люс
    0.40
    ὕ
    0.40
    ួយ
    0.40
    POSITIVE LOGITS
     sayıda
    0.52
     densité
    0.49
     oluştur
    0.48
     poiché
    0.46
     alır
    0.45
     കൊണ്ട്
    0.44
     kolom
    0.43
    ہ
    0.43
     Renata
    0.43
     बिना
    0.43
    Activations Density 0.001%

    No Known Activations