© 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. 130974
    Prev
    Next
    INDEX
    Explanations

    function definitions

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

    The neuron activates on numeric literals (integers or floating‐point numbers) in the text.

    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
     will
    -2.58
     to
    -2.30
    Both
    -2.19
    There
    -2.17
    %;
    -2.09
     only
    -2.08
     very
    -2.05
    <bos>
    -2.03
    It
    -2.02
     Both
    -2.02
    POSITIVE LOGITS
     ation
    2.19
     ity
    2.02
    皝
    1.96
     thier
    1.89
    Aplicaciones
    1.85
     pudieran
    1.84
    REASONS
    1.81
     diverses
    1.80
     willen
    1.80
    rás
    1.80
    Activations Density 0.025%

    No Known Activations