© 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. 10-GEMMASCOPE-RES-131K
    7. 69759
    Prev
    Next
    INDEX
    Explanations

    identifiers followed by values

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

    The neuron fires on numeric literal tokens (numbers, version numbers, IDs, constants) 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_10/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
    ”
    -2.11
    —”
    -2.03
     its
    -2.00
     has
    -1.97
     using
    -1.88
     well
    -1.88
     preparing
    -1.86
    ｱ
    -1.84
     just
    -1.81
     until
    -1.80
    POSITIVE LOGITS
     lamentable
    2.23
     -----
    2.13
    5
    1.85
     '-
    1.83
     obstin
    1.80
    这些
    1.77
     déplacements
    1.73
     corriger
    1.72
     incredi
    1.71
     reager
    1.71
    Activations Density 0.052%

    No Known Activations