© 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. 10-GEMMASCOPE-RES-131K
    7. 48237
    Prev
    Next
    INDEX
    Explanations

    constructors and class definitions

    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_10/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
    tehen
    -1.52
     exager
    -1.41
     essencial
    -1.40
    ぞれ
    -1.40
     gardien
    -1.38
     یکی
    -1.36
    Manfaat
    -1.36
     Perlu
    -1.34
    klinik
    -1.31
    lblNewLabel
    -1.30
    POSITIVE LOGITS
     with
    1.94
     that
    1.61
     like
    1.56
     usually
    1.55
     wöch
    1.53
     пръ
    1.52
     or
    1.49
     ganzes
    1.44
     mußte
    1.41
     before
    1.40
    Activations Density 0.005%

    No Known Activations