© 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. 75129
    Prev
    Next
    INDEX
    Explanations

    code

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

    This neuron fires on occurrences of the substring “cod”/“code” in identifiers or field names.

    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
    ?”
    -1.80
    ers
    -1.66
     ceux
    -1.55
    ,”
    -1.53
    …”
    -1.40
    .
    -1.34
    ophile
    -1.31
     also
    -1.30
    分区
    -1.30
    ”
    -1.30
    POSITIVE LOGITS
    亟
    1.65
    沬
    1.61
     hoppas
    1.52
    𖥧
    1.38
    ípio
    1.38
     jugu
    1.38
    Leírás
    1.38
     менее
    1.38
     pihaknya
    1.36
     anderen
    1.34
    Activations Density 0.006%

    No Known Activations