© 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. 80929
    Prev
    Next
    INDEX
    Explanations

    and/or lists

    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
    的重要
    -1.04
     сначала
    -1.02
    nemies
    -1.01
    ύτε
    -1.01
     faldas
    -0.98
    真正的
    -0.97
     längst
    -0.96
     כאשר
    -0.95
     simplemente
    -0.94
     fueran
    -0.93
    POSITIVE LOGITS
     others
    2.86
     its
    2.84
     other
    2.27
     any
    2.00
     related
    1.85
    others
    1.84
     many
    1.80
     similar
    1.73
     subsequent
    1.73
     the
    1.62
    Activations Density 0.063%

    No Known Activations