© 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. 119880
    Prev
    Next
    INDEX
    Explanations

    teams clubs sunset advantage result birds civil

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

    figures , @ , type

    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
     популя
    0.52
     glauben
    0.51
    สุขภาพ
    0.51
     quail
    0.50
     કારણે
    0.50
     ಸೇರಿದ
    0.48
     Saúde
    0.48
    藥
    0.47
    ण्डल
    0.47
    訊
    0.46
    POSITIVE LOGITS
    ikk
    0.50
    oves
    0.48
    ibir
    0.46
    rosse
    0.45
    ordo
    0.45
    qq
    0.45
    overe
    0.45
    ampion
    0.45
    dre
    0.45
     airbag
    0.45
    Activations Density 0.000%

    No Known Activations