© 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. 86901
    Prev
    Next
    INDEX
    Explanations

    singleton and instance creation

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

    The neuron consistently activates on the token “instance,” identifying occurrences of that word in code contexts.

    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
     unſ
    -2.48
    螣
    -2.23
     produttore
    -2.19
    廕
    -2.17
     eccellente
    -2.16
    甞
    -2.13
    銠
    -2.08
    嫑
    -2.08
    朏
    -1.99
     但
    -1.97
    POSITIVE LOGITS
     After
    2.81
    <bos>
    2.80
    Pgina
    2.45
    al
    2.36
     For
    2.36
     Generally
    2.33
     για
    2.33
     Since
    2.28
     digitais
    2.22
    䉴
    2.20
    Activations Density 0.004%

    No Known Activations