© 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. 60508
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

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

    The neuron is detecting numeric literal tokens (numbers) in structured text like JSON or 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
    0
    -1.80
    .
    -1.77
     sélections
    -1.73
     tiroirs
    -1.64
    byshire
    -1.63
     matières
    -1.63
    などなど
    -1.62
     marchandises
    -1.62
     Méri
    -1.58
     disques
    -1.57
    POSITIVE LOGITS
     these
    2.14
     a
    1.92
     some
    1.76
     it
    1.75
     at
    1.72
    n
    1.62
     there
    1.59
    </h2>
    1.58
    ógicos
    1.56
     situated
    1.50
    Activations Density 0.007%

    No Known Activations