© 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. 66255
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
     some
    -1.09
     eight
    -1.08
     it
    -1.07
    毎月
    -1.03
     truly
    -1.02
     a
    -1.00
     nine
    -1.00
     what
    -0.97
    ၅
    -0.96
     nueva
    -0.93
    POSITIVE LOGITS
     suscit
    1.10
     différentes
    1.00
    fifty
    0.95
    richten
    0.91
     bose
    0.91
     SEVER
    0.90
     useSelector
    0.90
     réduire
    0.90
    sprüng
    0.88
    と考えて
    0.88
    Activations Density 0.113%

    No Known Activations