© 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. 14236
    Prev
    Next
    INDEX
    Explanations

    character codes and digits

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

    The neuron strongly activates on individual hexadecimal‐style characters (digits 0–9 and A–F) in code or data.

    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
     for
    -1.82
     There
    -1.77
     it
    -1.69
     an
    -1.61
     While
    -1.60
     Almost
    -1.55
     on
    -1.54
     Despite
    -1.52
     For
    -1.52
     During
    -1.52
    POSITIVE LOGITS
     BECAUSE
    1.57
    still
    1.50
    抡
    1.48
    🫃
    1.48
     OFFER
    1.48
     Dinas
    1.44
     EVEN
    1.44
    缡
    1.41
    trying
    1.41
     diriger
    1.41
    Activations Density 0.001%

    No Known Activations