© 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. 93670
    Prev
    Next
    INDEX
    Explanations

    labels for data structures

    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
    jpeg
    -0.73
     G
    -0.72
     Вт
    -0.70
     Meghan
    -0.70
    WP
    -0.69
    trane
    -0.68
    ्
    -0.67
    setValue
    -0.65
     Giving
    -0.64
     Eq
    -0.64
    POSITIVE LOGITS
    angler
    0.75
     symbolic
    0.75
     huiles
    0.74
    废话
    0.73
    Symbolic
    0.73
    Plano
    0.71
     Symbolic
    0.71
    反应过来
    0.71
    VY
    0.71
     Cochin
    0.69
    Activations Density 0.084%

    No Known Activations