© 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. 34-GEMMASCOPE-RES-131K
    7. 33783
    Prev
    Next
    INDEX
    Explanations

    code structure indicators

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

    The neuron activates on numeric literal tokens (pure digit sequences) in code/JSON.

    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
    eniendo
    -0.82
     Sergey
    -0.74
    вила
    -0.73
    ILabel
    -0.73
     Kristine
    -0.71
    Dougall
    -0.69
    elsif
    -0.69
     riparian
    -0.69
    ALG
    -0.69
     exactement
    -0.68
    POSITIVE LOGITS
    HttpStatusCode
    0.89
     Status
    0.81
     Leiden
    0.75
    theoretical
    0.74
    moveToFirst
    0.69
    Schwarz
    0.69
    ђе
    0.68
    טה
    0.67
    äm
    0.67
     bos
    0.67
    Activations Density 0.019%

    No Known Activations