© 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. 10-GEMMASCOPE-RES-131K
    7. 130312
    Prev
    Next
    INDEX
    Explanations

    programming, scientific, or technical terms

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

    The neuron fires on comma punctuation marks.

    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
    </h3>
    -2.31
    _
    -2.30
    ↵
    -2.22
    #
    -2.11
     lively
    -2.09
    al
    -2.08
    de
    -2.05
    ‘
    -2.05
     nicely
    -2.02
    "
    -1.98
    POSITIVE LOGITS
     Garantie
    2.33
    蓠
    2.22
     doivent
    2.19
    Спасылкі
    2.13
    
    2.11
    abilidad
    2.05
    はある
    2.03
    
    2.03
    
    2.03
    EndContext
    2.02
    Activations Density 0.000%

    No Known Activations