© 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. 98459
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     latest
    -0.85
    Thirty
    -0.82
     Latest
    -0.82
    Twenty
    -0.82
     平成
    -0.81
    МЕН
    -0.80
    putAll
    -0.80
    Latest
    -0.78
     Thirty
    -0.77
     ২০১
    -0.77
    POSITIVE LOGITS
     ۱۲
    1.09
     ۱۱
    0.98
    auto
    0.93
    นะนำ
    0.84
    AutoScale
    0.80
    ishment
    0.79
    twelve
    0.79
     suom
    0.79
     ١
    0.79
     gustado
    0.78
    Activations Density 0.003%

    No Known Activations