© 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. 34-GEMMASCOPE-RES-131K
    7. 77885
    Prev
    Next
    INDEX
    Explanations

    code, configuration, and data structures

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

    The neuron consistently activates on numeric literal tokens (large numbers) 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_34/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
     tigre
    -0.82
     pewno
    -0.81
    ſten
    -0.79
     Deckel
    -0.78
    /*++
    -0.77
    Tage
    -0.77
     brosse
    -0.76
    Transcriptie
    -0.75
     trebuie
    -0.75
     vicente
    -0.74
    POSITIVE LOGITS
     deflate
    0.86
    ORY
    0.84
    дат
    0.79
     harden
    0.73
     skater
    0.71
     caminho
    0.71
    ющим
    0.71
    ory
    0.71
    COLL
    0.71
    restriction
    0.70
    Activations Density 0.016%

    No Known Activations