© 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. 59561
    Prev
    Next
    INDEX
    Explanations

    assigning or declaring programming variables

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

    The neuron fires on code identifiers—especially variable or object names—in programming 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_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
     incluindo
    -1.59
     produttore
    -1.56
    itattu
    -1.51
    
    -1.47
     علاوه
    -1.46
     collegamento
    -1.45
     ۱۳۸
    -1.44
     einschließlich
    -1.43
     outside
    -1.41
     whether
    -1.35
    POSITIVE LOGITS
     =
    1.65
    :
    1.62
    .
    1.41
    縝
    1.29
    Statut
    1.27
    _
    1.27
    伤感
    1.25
    kań
    1.24
    }
    1.21
     révèle
    1.20
    Activations Density 0.071%

    No Known Activations