© 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. 60569
    Prev
    Next
    INDEX
    Explanations

    code programming language constructs

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

    The neuron fires on uncommon, content-bearing tokens—mostly domain-specific nouns, verbs, and code identifiers—rather than on common function words.

    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
     何
    -0.70
     nedost
    -0.70
    Bài
    -0.69
    Durante
    -0.68
    Jar
    -0.66
    何
    -0.65
    ="#"
    -0.64
    github
    -0.64
    Publication
    -0.63
    Burg
    -0.63
    POSITIVE LOGITS
    elde
    0.82
     Оль
    0.78
    久了
    0.77
    Reveal
    0.75
     نوج
    0.74
    REPO
    0.73
    slightly
    0.73
    nfs
    0.73
    товых
    0.73
     rurale
    0.71
    Activations Density 0.385%

    No Known Activations