© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99720
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    The neuron fires on numeric literal tokens in code (e.g., integer constants).

    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
     ヶ
    -2.09
     tiens
    -2.02
    んご
    -1.95
    옳
    -1.94
    ingeki
    -1.93
     efficaces
    -1.85
     jota
    -1.84
     الدولي
    -1.83
     ژان
    -1.82
    莚
    -1.81
    POSITIVE LOGITS
     
    2.91
     predominantly
    2.23
     extremely
    2.19
    becomes
    2.16
     decidedly
    2.13
     exceedingly
    2.06
      
    2.06
     wonderfully
    2.05
    showed
    2.05
     delightfully
    2.03
    Activations Density 0.048%

    No Known Activations