© 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. 22-GEMMASCOPE-RES-131K
    4. 68921
    Prev
    Next
    INDEX
    Explanations

    McGean, Sarles, up to

    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_22/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
     Alembic
    -1.04
     vostre
    -1.04
     excur
    -1.03
     ingenu
    -1.02
     ผู้
    -1.01
     [{
    
    -0.99
    他们在
    -0.98
    給你
    -0.98
    ené
    -0.97
     ваших
    -0.97
    POSITIVE LOGITS
     but
    1.34
     would
    1.30
     possible
    1.16
     or
    1.09
     so
    1.05
     without
    1.04
    inquirer
    1.04
     this
    0.98
     either
    0.96
     olisi
    0.96
    Activations Density 0.015%

    No Known Activations