© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21141
    Prev
    Next
    INDEX
    Explanations

    arrow operator or function chaining

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

    The neuron is detecting use of the “->” arrow operator in code (member access or method chaining).

    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
    </h1>
    -2.27
    ሷ
    -2.20
    祧
    -2.20
    ၟ
    -2.09
    푣
    -2.00
    }
    -1.94
    可能有
    -1.93
    “,
    -1.91
    讎
    -1.91
    whelmed
    -1.89
    POSITIVE LOGITS
    ти
    1.98
     However
    1.94
    pisah
    1.84
     
    1.79
     acceptez
    1.70
    ピアノ
    1.67
    iffance
    1.66
     предложи
    1.65
     núcleos
    1.63
     вышел
    1.63
    Activations Density 0.001%

    No Known Activations