© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60426
    Prev
    Next
    INDEX
    Explanations

    key code identifier

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

    The neuron responds strongly to programming identifiers and key names (e.g. function or property names, JSON field names) in code 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_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
     ハーフ
    -0.84
     Balan
    -0.74
    createTextNode
    -0.74
     مكتب
    -0.73
     assai
    -0.73
    tidumbre
    -0.72
     地図
    -0.72
    📡
    -0.72
    haël
    -0.72
    もうすぐ
    -0.71
    POSITIVE LOGITS
     slug
    1.80
    slug
    1.74
     key
    1.72
     code
    1.68
    Slug
    1.49
    Key
    1.32
     identifier
    1.30
     Slug
    1.26
     slugs
    1.24
    KEY
    1.22
    Activations Density 0.049%

    No Known Activations