© 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. 26584
    Prev
    Next
    INDEX
    Explanations

    code and technical markup

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

    The neuron strongly activates on numeric tokens (digits or 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
    DDS
    -0.88
    Opinión
    -0.82
    skal
    -0.82
    wss
    -0.75
     ramen
    -0.74
    ־ה
    -0.74
     lapse
    -0.73
    люсы
    -0.73
    diksi
    -0.73
    Awwww
    -0.72
    POSITIVE LOGITS
    Crypto
    0.83
    oczes
    0.81
     eius
    0.79
    셸
    0.79
    Kara
    0.79
    áu
    0.78
     EURO
    0.77
     青
    0.76
     сцена
    0.75
    Airlines
    0.74
    Activations Density 0.023%

    No Known Activations