© 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. 34-GEMMASCOPE-RES-131K
    7. 45452
    Prev
    Next
    INDEX
    Explanations

    Fellow Lagosians / Q:

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

    The neuron strongly activates on numerals and digit‐based tokens (i.e. numbers and number sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Initializer
    -0.71
    パーク
    -0.68
    currentColor
    -0.68
    /***
    -0.68
    XCTAssertEqual
    -0.66
    cuer
    -0.66
    togram
    -0.65
     тока
    -0.65
    雳
    -0.65
    ņa
    -0.64
    POSITIVE LOGITS
     Atiku
    1.05
    Presidential
    0.91
     polling
    0.87
     rigging
    0.85
     Presidential
    0.83
     Bloomberg
    0.81
    Kale
    0.80
     DATA
    0.79
    ciudad
    0.79
    Oby
    0.79
    Activations Density 0.011%

    No Known Activations