© 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. 44299
    Prev
    Next
    INDEX
    Explanations

    solidity, ethereum, usercontent

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

    The neuron activates on mentions of blockchain smart‐contract terminology, especially the words “solidity” and “ethereum.”

    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
    as
    -3.38
    .
    -3.09
     become
    -2.55
    ?
    -2.47
    AN
    -2.47
    this
    -2.44
    _
    -2.33
     As
    -2.31
    ا
    -2.28
    IN
    -2.20
    POSITIVE LOGITS
    俛
    3.44
    肏
    2.53
     diki
    2.50
    馕
    2.38
    慙
    2.38
    歘
    2.34
    
    2.31
     torba
    2.31
    谂
    2.31
    Ruju
    2.30
    Activations Density 0.001%

    No Known Activations