© 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. 10-GEMMASCOPE-RES-131K
    7. 58692
    Prev
    Next
    INDEX
    Explanations

    software component names

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

    This neuron activates on named code identifiers—library, module, or class names (e.g., framework or project names) in source files.

    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
    <blockquote>
    -1.27
    ด์
    -1.19
     الاجتماعية
    -1.17
     habituellement
    -1.16
    数据
    -1.16
    hithe
    -1.15
    ラス
    -1.14
    
    -1.14
     llamaba
    -1.12
    ACIAS
    -1.11
    POSITIVE LOGITS
    </h1>
    1.17
     amarela
    1.02
     facilitated
    1.02
     světa
    1.00
    Award
    1.00
    Provided
    1.00
     conséquences
    0.99
     heutigen
    0.98
     anhand
    0.98
    alphabet
    0.97
    Activations Density 0.038%

    No Known Activations