© 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. 22-GEMMASCOPE-RES-131K
    7. 12625
    Prev
    Next
    INDEX
    Explanations

    code declarations and assignments

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

    The neuron is chiefly detecting code‐style identifiers and keywords—tokens like variable or function names and other programming symbols.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    まずは
    -1.07
    뭘
    -1.06
    fő
    -1.02
    sists
    -1.02
    könyv
    -1.00
    
    -0.98
    fications
    -0.98
    resultado
    -0.97
    🤯
    -0.96
    meler
    -0.95
    POSITIVE LOGITS
     ngờ
    0.92
     also
    0.91
     epidem
    0.90
     ibang
    0.90
     curar
    0.90
     specific
    0.89
     contribution
    0.87
     odonto
    0.86
    Substances
    0.85
     Κυ
    0.85
    Activations Density 0.009%

    No Known Activations