© 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. 11297
    Prev
    Next
    INDEX
    Explanations

    emphasized words

    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
    The
    -1.45
     something
    -1.34
     then
    -1.33
     teus
    -1.30
     his
    -1.30
    na
    -1.27
     just
    -1.27
    After
    -1.26
    using
    -1.25
    Other
    -1.24
    POSITIVE LOGITS
     savons
    1.54
    理会
    1.45
     différences
    1.43
     from
    1.41
    zegovina
    1.41
    峮
    1.36
    phonie
    1.35
     который
    1.35
    omore
    1.33
     elke
    1.31
    Activations Density 0.012%

    No Known Activations