© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77204
    Prev
    Next
    INDEX
    Explanations

    method calls and object instantiation

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

    This neuron is tuned to picks up on code function or method invocations—that is, identifiers (often in CamelCase or special method names) immediately followed by parentheses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     assisti
    -0.86
    ві
    -0.81
    adaptiveStyles
    -0.76
    ٔ
    -0.76
     เมื่อ
    -0.73
     betreffenden
    -0.73
    习近平
    -0.72
    bParam
    -0.71
    ආ
    -0.71
     あん
    -0.70
    POSITIVE LOGITS
    ()
    3.25
    ()
    
    2.45
    ().
    2.31
    (),
    2.20
    ():
    2.11
    ()"
    1.95
    ()-
    1.85
    ())
    1.77
    ()`
    1.77
    ();
    1.76
    Activations Density 0.118%

    No Known Activations