© 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. 73598
    Prev
    Next
    INDEX
    Explanations

    solidity, solvent, bindings, go

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

    The neuron fires on occurrences of the Solidity programming language keyword (e.g. “solidity” in pragma or code declarations).

    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
    ）；
    -1.88
    '];
    -1.80
    </h5>
    -1.79
    寕
    -1.75
     âmes
    -1.75
    镬
    -1.74
     neuer
    -1.74
     駅前
    -1.73
     شدن
    -1.73
     doprav
    -1.71
    POSITIVE LOGITS
    2
    2.34
    You
    2.22
    this
    2.08
    1
    1.96
    本当に
    1.95
    ка
    1.91
    ième
    1.89
    在
    1.89
    你的
    1.86
    7
    1.84
    Activations Density 0.001%

    No Known Activations