© 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. 65646
    Prev
    Next
    INDEX
    Explanations

    code formatting markers

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

    This neuron detects numeric tokens (digits or numeric literals) within code or structured 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
     outcrop
    -0.87
     apple
    -0.80
    ogne
    -0.78
     taxi
    -0.77
     statue
    -0.75
     hamburger
    -0.75
     teacher
    -0.75
     cow
    -0.74
    これも
    -0.74
    arus
    -0.73
    POSITIVE LOGITS
     counterparts
    0.99
    adapted
    0.90
     counterpart
    0.88
     undangan
    0.84
     pengusaha
    0.84
     Semoga
    0.83
     zondag
    0.83
    𝚕
    0.83
    equivalent
    0.82
     pengurus
    0.81
    Activations Density 0.013%

    No Known Activations