© 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. 22-GEMMASCOPE-RES-131K
    4. 36469
    Prev
    Next
    INDEX
    Explanations

    programming code function calls

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

    The neuron is selectively activating on programming API or library function names (identifiers like array_keys, mysql_query, parseInt, REPLACE, 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_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
    畾
    -1.27
     {
    
    
    -1.16
     "/")
    -1.09
     “
    -1.07
     Problemas
    -1.06
     notte
    -1.06
    Bulg
    -1.06
    ❓
    -1.05
     presentazione
    -1.03
    }));
    
    -1.02
    POSITIVE LOGITS
     of
    1.38
     one
    1.28
     you
    1.23
    (
    1.20
    ()
    1.16
     it
    1.09
     etc
    1.09
    </strong>
    1.09
     function
    1.02
     also
    0.99
    Activations Density 0.155%

    No Known Activations