© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78223
    Prev
    Next
    INDEX
    Explanations

    std:: namespace resolution

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

    The neuron fires on tokens that name programming libraries or namespaces (e.g. std, np, java, scala).

    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
     even
    -1.10
     so
    -1.07
    !!
    -1.00
    </td>
    -0.98
    </thead>
    -0.95
    !!!
    -0.94
     даже
    -0.92
     especially
    -0.91
    !!!!!
    -0.91
     حتی
    -0.90
    POSITIVE LOGITS
     ausein
    1.15
    phòng
    1.13
     både
    1.13
    burgers
    1.11
     spelen
    1.09
    😠
    1.09
     zowel
    1.08
    wwwwwwww
    1.07
     dépenses
    1.06
    kệ
    1.06
    Activations Density 0.025%

    No Known Activations