© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65749
    Prev
    Next
    INDEX
    Explanations

    types 2 and 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     youngster
    -0.89
    のでしょう
    -0.88
    明顯
    -0.85
     spéciale
    -0.85
    読む
    -0.85
     vistazo
    -0.85
     vorgesch
    -0.85
    Perhaps
    -0.84
     enemigo
    -0.81
     кстати
    -0.80
    POSITIVE LOGITS
     приготовить
    1.13
    '''
    1.09
     leste
    1.03
    `
    1.02
     metu
    1.01
    ">>
    0.96
    ఎ
    0.96
    nienia
    0.96
    ⾔
    0.95
     ketahui
    0.94
    Activations Density 0.112%

    No Known Activations