© 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. 84836
    Prev
    Next
    INDEX
    Explanations

    code structure declarations

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

    The neuron activates on tokens that introduce or name programming‐language declarations (e.g. “struct,” “function,” “Cross,” etc.).

    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
    توضی
    -0.84
    ֹת
    -0.84
    jdons
    -0.76
     Panama
    -0.76
    geslacht
    -0.75
    ल्या
    -0.75
    Adapun
    -0.75
    Kenapa
    -0.75
    Bagaimana
    -0.74
    Tetapi
    -0.74
    POSITIVE LOGITS
     ,
    0.85
     share
    0.84
    ²
    0.81
     дальней
    0.80
    ——
    0.78
    Virtual
    0.78
     участок
    0.78
    esac
    0.77
    ****************
    0.75
     Cramer
    0.75
    Activations Density 0.002%

    No Known Activations