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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99775
    Prev
    Next
    INDEX
    Explanations

    hyphenated words

    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
     secondaires
    -0.95
    🗑
    -0.85
     Holocaust
    -0.85
    $\
    -0.84
    [];
    -0.80
    Reduce
    -0.79
     immédi
    -0.79
     понимаю
    -0.77
     pengembangan
    -0.77
    ?)
    -0.77
    POSITIVE LOGITS
     until
    1.11
     up
    1.04
     jusqu
    0.99
     hanggang
    0.98
     sampai
    0.97
     Hasta
    0.95
     hasta
    0.93
     till
    0.89
     kuni
    0.86
    hasta
    0.84
    Activations Density 0.010%

    No Known Activations