© 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. 70857
    Prev
    Next
    INDEX
    Explanations

    how to explain or do

    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
    不管是
    -1.70
     to
    -1.63
     académica
    -1.47
    －－
    -1.47
     möjlighet
    -1.46
    越来越多
    -1.46
     energética
    -1.44
     geográfica
    -1.42
     orgánica
    -1.42
     abilities
    -1.41
    POSITIVE LOGITS
     of
    2.58
     and
    1.52
     thoſe
    1.52
     a
    1.46
    而不
    1.45
     générales
    1.42
    álise
    1.42
     kwiat
    1.39
    ÇO
    1.37
     article
    1.34
    Activations Density 0.118%

    No Known Activations