© 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. 72275
    Prev
    Next
    INDEX
    Explanations

    documentation comments

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

    The neuron activates on standalone numeric literals (numbers) 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
    SDAY
    -0.96
    daya
    -0.96
    <bos>
    -0.95
    MANUEL
    -0.94
    ΕΛ
    -0.92
    FOLIO
    -0.91
    GERS
    -0.90
    fromUtf
    -0.90
    ERICK
    -0.90
    LETT
    -0.90
    POSITIVE LOGITS
    compared
    1.11
     nô
    1.00
     trám
    0.98
    espacio
    0.98
     będzie
    0.98
     probablemente
    0.97
     semej
    0.97
     будет
    0.97
    resumen
    0.96
     atraer
    0.95
    Activations Density 0.001%

    No Known Activations