© 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. 26946
    Prev
    Next
    INDEX
    Explanations

    tuneable, integration, com

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

    The neuron fires on standalone numeric tokens (literal numbers) in code or data (e.g. “119”, “99”, “86”, “113”).

    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
    ptian
    -0.91
    Like
    -0.91
    metra
    -0.90
     ../
    -0.86
    смотря
    -0.85
     ervaring
    -0.84
    antara
    -0.84
    †
    -0.83
     who
    -0.83
    https
    -0.83
    POSITIVE LOGITS
    éditeur
    1.09
     mostrarse
    1.07
     jestli
    1.03
    いても
    0.99
    iotti
    0.98
    makes
    0.97
    璘
    0.96
     referirse
    0.94
    too
    0.92
     limão
    0.92
    Activations Density 0.000%

    No Known Activations