© 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. 12371
    Prev
    Next
    INDEX
    Explanations

    Fight Night, Maxim, Wales

    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
    ('../../../
    -1.64
     obicei
    -1.64
    ('../../
    -1.63
     szüks
    -1.59
    CITATION
    -1.58
    wasan
    -1.58
    ابراین
    -1.51
    laat
    -1.49
     piele
    -1.48
     azonban
    -1.47
    POSITIVE LOGITS
     different
    1.63
     are
    1.63
    to
    1.59
    the
    1.56
     +
    1.47
     various
    1.42
     $
    1.40
     -
    1.39
     .
    1.38
     or
    1.37
    Activations Density 0.173%

    No Known Activations