© 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. 22-GEMMASCOPE-RES-131K
    7. 15160
    Prev
    Next
    INDEX
    Explanations

    citations with [@pone

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

    The neuron fires on tokens that are purely numeric (e.g. standalone numbers, timestamps, counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     pim
    -0.90
     Noviembre
    -0.89
     inev
    -0.89
     adress
    -0.88
     tenter
    -0.86
     dispo
    -0.86
    kissen
    -0.85
     poursu
    -0.84
     画像
    -0.84
     dosa
    -0.84
    POSITIVE LOGITS
     not
    0.91
     препарат
    0.90
     zcela
    0.87
     most
    0.85
     such
    0.85
    XCTAssertEqual
    0.82
    ysaccharide
    0.81
     simple
    0.80
    allowNull
    0.80
     so
    0.79
    Activations Density 0.045%

    No Known Activations