© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39190
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

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

    The neuron detects numeric literal tokens (numbers) in code or 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_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
     (
    -1.16
     where
    -1.05
     让
    -1.05
     девочек
    -1.02
     рік
    -0.96
    CURLOPT
    -0.96
     девушек
    -0.96
    ३
    -0.96
    parka
    -0.95
     inspiradoras
    -0.92
    POSITIVE LOGITS
    푉
    1.13
    Ге
    1.07
     οποία
    1.02
    Hilsen
    1.01
    ifies
    0.99
    chooser
    0.98
     ciertos
    0.97
    attendre
    0.96
    Passo
    0.96
    -;
    0.96
    Activations Density 0.003%

    No Known Activations