© 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. 13254
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
     betalen
    -1.03
    olympic
    -1.03
     our
    -1.02
     who
    -0.97
    virtu
    -0.95
    нял
    -0.95
    scc
    -0.93
    drake
    -0.93
    rasında
    -0.92
    engertian
    -0.92
    POSITIVE LOGITS
     afore
    1.13
    aneity
    1.11
     foglie
    0.97
    鰹
    0.90
    queness
    0.90
     trattano
    0.89
     болезни
    0.87
    當然
    0.87
    凝土
    0.87
    uating
    0.86
    Activations Density 0.043%

    No Known Activations