© 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. 98169
    Prev
    Next
    INDEX
    Explanations

    references, citations, figures

    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
     dessas
    -0.90
    Procedimento
    -0.90
     seksi
    -0.87
     metodi
    -0.87
    ensus
    -0.87
     kağıt
    -0.84
    twenty
    -0.83
     BIBLIOGRAPHY
    -0.82
    kontak
    -0.82
    äle
    -0.82
    POSITIVE LOGITS
    setStyleSheet
    1.01
    ‌است
    0.91
     Sect
    0.88
    [:
    0.84
    <sup>
    0.83
     in
    0.81
    ........
    0.80
     cassettes
    0.78
    !!!!
    0.78
     via
    0.77
    Activations Density 0.002%

    No Known Activations