© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99018
    Prev
    Next
    INDEX
    Explanations

    pluralization and string literals

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

    The neuron fires on programming‐related tokens and syntax constructs (e.g. code identifiers, meta declarations, template markers, and similar technical elements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     وصل
    -0.83
    CLUDE
    -0.77
    смарт
    -0.77
     Dand
    -0.77
     nélkül
    -0.77
    bilità
    -0.77
    াহ
    -0.76
    cemment
    -0.75
     TUT
    -0.73
     написать
    -0.73
    POSITIVE LOGITS
    Plural
    0.87
     organizer
    0.81
     plural
    0.80
     over
    0.80
    plural
    0.76
     Organizer
    0.76
     csin
    0.73
     verbose
    0.70
     propOrder
    0.69
    iança
    0.68
    Activations Density 0.006%

    No Known Activations