© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 69942
    Prev
    Next
    INDEX
    Explanations

    licenses and table components

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

    The neuron is picking up on programming‐oriented tokens—HTML tags, framework directives, code keywords, and other code‐snippet syntax.

    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
    五郎
    -0.81
    nieuw
    -0.79
     marrone
    -0.78
     Să
    -0.77
     perdre
    -0.77
     Moderne
    -0.77
    Étienne
    -0.77
     عراق
    -0.75
     yards
    -0.75
    StatusBadRequest
    -0.75
    POSITIVE LOGITS
    이며
    0.82
    JMenuItem
    0.81
     Ben
    0.79
     Tar
    0.77
     Eclipse
    0.74
     Aussch
    0.73
     sw
    0.73
     impress
    0.70
     Lehre
    0.70
     Ny
    0.69
    Activations Density 0.005%

    No Known Activations