© 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. 34-GEMMASCOPE-RES-131K
    7. 106895
    Prev
    Next
    INDEX
    Explanations

    blockchain contract calls and selectors

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

    The neuron detects programming‐language code tokens—identifiers, keywords, version numbers, and library names—i.e. text from code snippets.

    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
     download
    -0.82
     downloaded
    -0.80
     Jeddah
    -0.77
     doanh
    -0.74
    veröffentlichung
    -0.73
     چاپ
    -0.73
     delay
    -0.71
    ダウンロード
    -0.70
     Download
    -0.67
    tias
    -0.67
    POSITIVE LOGITS
     calldata
    1.22
     call
    1.12
    Call
    1.10
    selector
    1.10
     selector
    1.09
     abi
    1.09
    abi
    1.08
    CALL
    1.07
    Selector
    1.06
    ABI
    1.05
    Activations Density 0.011%

    No Known Activations