© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99291
    Prev
    Next
    INDEX
    Explanations

    Please note, that

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on instances of the word “Note,” (i.e. editorial or aside markers beginning with “Note,”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     those
    -1.99
     Gelegenheit
    -1.54
     that
    -1.52
     duża
    -1.38
     основании
    -1.35
     gewiß
    -1.34
     irgend
    -1.34
     then
    -1.31
    icali
    -1.31
     similar
    -1.30
    POSITIVE LOGITS
    躥
    1.89
    我们的
    1.67
    they
    1.49
    曏
    1.47
    憷
    1.45
     idyl
    1.44
     {
    1.41
    焢
    1.41
    Наши
    1.39
     padang
    1.39
    Activations Density 0.048%

    No Known Activations