© 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. 73558
    Prev
    Next
    INDEX
    Explanations

    CSS declarations and properties

    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
     or
    -1.12
    kými
    -1.00
     on
    -0.95
     Equally
    -0.93
     Ві
    -0.93
    -
    -0.91
     by
    -0.91
    ÇÕES
    -0.88
    aların
    -0.88
     since
    -0.88
    POSITIVE LOGITS
     its
    1.15
    Jährige
    1.02
     guarda
    1.02
     extré
    1.00
    曬
    0.99
     eccl
    0.98
     potencia
    0.98
    Neden
    0.94
    ;.
    0.94
    figure
    0.94
    Activations Density 0.007%

    No Known Activations