© 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. 73417
    Prev
    Next
    INDEX
    Explanations

    compound technical terms

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

    The neuron detects numeric literals (sequences of digits) in code.

    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
    יתוף
    -0.91
     anser
    -0.89
    魮
    -0.88
    Noo
    -0.88
    ligkeit
    -0.88
    さは
    -0.88
    Makanan
    -0.88
    ڧ
    -0.87
    IKit
    -0.86
    wnie
    -0.85
    POSITIVE LOGITS
    </i>
    0.91
    </em>
    0.89
    see
    0.85
    を参照
    0.84
     becomes
    0.83
     accounts
    0.81
    usata
    0.81
    </b>
    0.80
    <
    0.79
    វ
    0.79
    Activations Density 0.006%

    No Known Activations