© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101783
    Prev
    Next
    INDEX
    Explanations

    specifying a destination or assignment

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

    This neuron fires on the parameter-label tokens “from:” and “to:” in code, i.e. when named arguments or hash keys ‘from’ or ‘to’ appear.

    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
    錀
    -2.17
    to
    -1.89
     vuitton
    -1.86
    </i>
    -1.86
     rute
    -1.84
    </h3>
    -1.80
    多种
    -1.77
    䉴
    -1.74
    ┇
    -1.74
    …”
    -1.74
    POSITIVE LOGITS
     inextrica
    1.88
    焄
    1.84
    瀦
    1.73
    replyreport
    1.70
     shudder
    1.70
     vigueur
    1.66
    mathbf
    1.66
    能在
    1.63
    tedì
    1.63
    渼
    1.60
    Activations Density 0.008%

    No Known Activations