© 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. 82412
    Prev
    Next
    INDEX
    Explanations

    Some or few quantifiers

    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
    amines
    -0.93
     lot
    -0.91
    那些
    -0.90
     такое
    -0.88
     brindar
    -0.88
    Neder
    -0.85
     ナチュラル
    -0.84
     นิ้ว
    -0.83
     каждую
    -0.82
     loads
    -0.81
    POSITIVE LOGITS
    wherein
    1.34
    1.05
    WithMany
    1.03
    things
    1.02
    ones
    1.00
    0.98
    ()))
    0.95
    綃
    0.95
    wachsenen
    0.94
    digde
    0.94
    Activations Density 0.026%

    No Known Activations