© 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. 11238
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and equations

    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
     from
    -1.46
     only
    -1.27
     because
    -1.17
     pendapat
    -1.12
     that
    -1.06
     kajian
    -1.05
     this
    -1.03
     pemikiran
    -1.00
     to
    -0.98
    vska
    -0.98
    POSITIVE LOGITS
     Afgan
    1.13
     uſ
    1.04
     каждой
    1.00
     fecond
    0.99
    COST
    0.97
     Sovi
    0.97
     birbir
    0.93
    OREM
    0.92
    Diagnosis
    0.90
     Nomination
    0.90
    Activations Density 0.009%

    No Known Activations