© 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. 14921
    Prev
    Next
    INDEX
    Explanations

    teams, defender, edge, maps, assistant, graph

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

    The neuron detects mentions of specific software or tech product names (i.e., brand/application names).

    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
     This
    -1.84
     of
    -1.72
     Selasa
    -1.52
    也
    -1.46
    少ない
    -1.46
     Krzyż
    -1.46
    第七
    -1.44
    ос
    -1.44
    сос
    -1.38
     Before
    -1.36
    POSITIVE LOGITS
    会导致
    1.56
    ܃
    1.55
    她們
    1.55
    他們的
    1.54
     LIVES
    1.54
    نگار
    1.49
    三個
    1.48
    Algunas
    1.48
    Síguenos
    1.48
     ASPECTS
    1.45
    Activations Density 0.016%

    No Known Activations