© 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. 33585
    Prev
    Next
    INDEX
    Explanations

    proper nouns and code snippets

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

    The neuron selectively activates on subword pieces that form proper‐name fragments, acronyms, or other unusual capitalized/technical identifiers.

    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
     container
    -0.87
    ence
    -0.80
     恵
    -0.79
    body
    -0.78
    cuerpo
    -0.74
    unisex
    -0.72
     body
    -0.71
    container
    -0.71
    erkek
    -0.70
     crumble
    -0.69
    POSITIVE LOGITS
    BIR
    0.78
    子弹
    0.75
    🌓
    0.75
    nowa
    0.74
     Metadata
    0.73
     locul
    0.73
     croce
    0.73
    wir
    0.73
     omnium
    0.72
    PIX
    0.72
    Activations Density 0.062%

    No Known Activations