© 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. 101685
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with subscripts

    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
     its
    -2.39
     then
    -2.23
     if
    -1.73
     or
    -1.60
     її
    -1.52
     by
    -1.51
     её
    -1.44
    c
    -1.43
     both
    -1.43
    if
    -1.43
    POSITIVE LOGITS
     ombro
    1.56
    odziel
    1.50
     parachoque
    1.48
     anún
    1.44
    dass
    1.37
     frança
    1.36
     a
    1.34
     fevere
    1.32
     zů
    1.32
    wyczaj
    1.31
    Activations Density 0.025%

    No Known Activations