© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127913
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
     bluz
    -1.84
     normaux
    -1.79
     kabát
    -1.73
     plafon
    -1.66
     XXXI
    -1.65
     ARXIV
    -1.64
     XXIX
    -1.63
     sabah
    -1.63
     kompati
    -1.63
     XXVIII
    -1.63
    POSITIVE LOGITS
     will
    2.56
     to
    2.13
     of
    1.80
     for
    1.69
     in
    1.67
    to
    1.66
     de
    1.63
     D
    1.62
    te
    1.61
     d
    1.55
    Activations Density 0.024%

    No Known Activations