© 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. 99328
    Prev
    Next
    INDEX
    Explanations

    technology and industry terms

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

    The neuron strongly activates on specialized technical and engineering jargon—industry- and device-related terms that name fields, equipment, or processes.

    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
     lèvres
    -1.60
    </b>
    -1.56
    Dès
    -1.55
    archiviato
    -1.55
     pohod
    -1.53
    Ḡ
    -1.53
     食事
    -1.52
    Ť
    -1.52
     gewiß
    -1.51
    vaders
    -1.51
    POSITIVE LOGITS
     different
    1.59
    J
    1.58
     of
    1.57
    T
    1.53
     sometimes
    1.47
    K
    1.47
    ]
    1.45
     including
    1.45
    P
    1.44
     response
    1.43
    Activations Density 0.333%

    No Known Activations