© 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. 105927
    Prev
    Next
    INDEX
    Explanations

    programming constructs and object manipulation

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

    This neuron fires on programming‐style function or method call tokens (i.e. identifiers like alloc, initWith…, parse, append, querySelector, etc.).

    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
     estómago
    -1.45
    carros
    -1.36
    ILERS
    -1.34
    七年
    -1.27
     則
    -1.27
     mengerti
    -1.25
    わけではない
    -1.24
     oublier
    -1.21
    ikä
    -1.21
     daar
    -1.20
    POSITIVE LOGITS
     when
    1.94
     because
    1.83
     it
    1.73
     most
    1.70
     protože
    1.69
    .”
    1.63
     gdyż
    1.56
     more
    1.55
     ponieważ
    1.52
    }$.
    1.50
    Activations Density 0.020%

    No Known Activations