© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66290
    Prev
    Next
    INDEX
    Explanations

    infrastructure

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

    The neuron strongly responds to mentions of “infrastructure” or closely related public‐service and facility terms.

    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
    7
    -2.20
    泐
    -2.05
    Of
    -2.03
    塤
    -1.91
    ᥒ
    -1.91
    ꯶
    -1.89
    estão
    -1.87
    vého
    -1.86
    ⑉
    -1.86
    of
    -1.83
    POSITIVE LOGITS
    </h4>
    2.33
    .
    2.11
     beiden
    1.96
     continúas
    1.94
    恁
    1.91
    "
    1.88
     специфи
    1.86
     यदि
    1.86
    </sup>
    1.85
    на
    1.84
    Activations Density 0.008%

    No Known Activations