© 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. 99526
    Prev
    Next
    INDEX
    Explanations

    thumbnail image generation

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

    The neuron reliably fires on code tokens that look like function or method definitions (identifiers followed by parentheses).

    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
    an
    -5.06
    a
    -4.72
    e
    -3.67
    ing
    -3.64
    Of
    -3.55
    r
    -3.30
    на
    -3.14
    b
    -3.13
    P
    -3.11
    3
    -3.05
    POSITIVE LOGITS
    茘
    2.72
    惭
    2.55
    跸
    2.50
    𝗦
    2.45
    niająca
    2.41
    遊戯
    2.38
    呪術
    2.36
    囮
    2.36
     discerning
    2.34
    言った
    2.34
    Activations Density 0.005%

    No Known Activations