© 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. 10-GEMMASCOPE-RES-131K
    7. 59301
    Prev
    Next
    INDEX
    Explanations

    html form table button

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

    This neuron activates on identifiers used as element names, class names, or IDs in code (e.g. “text,” “label,” “slide,” “axis,” “link,” “menu,” “title,” etc.).

    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
     to
    -1.60
     in
    -1.38
     is
    -1.36
    
    -1.34
    Tanz
    -1.34
    、“
    -1.30
     jengibre
    -1.30
     failings
    -1.29
    死神
    -1.29
     márm
    -1.27
    POSITIVE LOGITS
    _
    2.19
     only
    1.98
    from
    1.75
     våra
    1.73
    they
    1.73
     these
    1.71
    e
    1.70
    倆
    1.70
    even
    1.70
     we
    1.70
    Activations Density 0.043%

    No Known Activations