© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 11819
    Prev
    Next
    INDEX
    Explanations

    degrees, AU, h

    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
    Capítulo
    -0.82
    なんか
    -0.75
    度は
    -0.73
     vaksinasi
    -0.71
    مية
    -0.70
    אח
    -0.70
     WEL
    -0.69
    ⠼
    -0.69
    jahtera
    -0.69
     Warrant
    -0.68
    POSITIVE LOGITS
     projected
    0.85
    ̋
    0.84
     Tai
    0.82
    hir
    0.80
     PA
    0.79
     Thi
    0.79
    kup
    0.77
     pixels
    0.76
     proyec
    0.76
    Ꮪ
    0.75
    Activations Density 0.018%

    No Known Activations