© 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. 98554
    Prev
    Next
    INDEX
    Explanations

    references like [@[number

    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
     pantal
    -0.91
    .../
    -0.84
    ::::::::::::::::
    -0.82
     xmm
    -0.82
     GEORG
    -0.81
    하며
    -0.80
     €)
    -0.79
     ieee
    -0.79
    quels
    -0.78
    :+
    -0.77
    POSITIVE LOGITS
     WHEN
    0.98
     sedang
    0.96
    When
    0.95
    when
    0.95
    正在
    0.91
    ülen
    0.91
    фикации
    0.90
     when
    0.87
     When
    0.86
     cruising
    0.86
    Activations Density 0.011%

    No Known Activations