© 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. 50397
    Prev
    Next
    INDEX
    Explanations

    listing of numbers and symbols

    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
     hoc
    -0.75
    Dtos
    -0.72
    baru
    -0.71
     mus
    -0.71
    完了
    -0.71
     Trop
    -0.70
     conservation
    -0.69
     präsentieren
    -0.69
    کنون
    -0.69
    Bayes
    -0.69
    POSITIVE LOGITS
    Miz
    0.87
    awia
    0.85
     coriander
    0.84
     Miz
    0.81
    ṭ
    0.80
    awi
    0.79
     awk
    0.77
    ㎡
    0.76
    iseaux
    0.75
    isateur
    0.75
    Activations Density 0.010%

    No Known Activations