© 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. 34-GEMMASCOPE-RES-131K
    7. 909
    Prev
    Next
    INDEX
    Explanations

    Quiz and introduction

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

    The neuron fires on numeric literal tokens (e.g. version numbers, data-attribute values) in code or markup.

    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
     مانند
    -0.89
    きて
    -0.82
    たまた
    -0.79
     globally
    -0.76
     Formerly
    -0.75
     tướng
    -0.74
    海軍
    -0.74
     melalui
    -0.74
     parfois
    -0.73
    μένου
    -0.72
    POSITIVE LOGITS
     href
    0.82
     laure
    0.80
     Quartz
    0.77
    Philippe
    0.77
     Birmingham
    0.77
     женщина
    0.77
     pane
    0.76
     亜
    0.76
    Chorus
    0.76
     Philippe
    0.75
    Activations Density 0.006%

    No Known Activations