© 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. 21222
    Prev
    Next
    INDEX
    Explanations

    military and vehicles

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

    The neuron strongly activates on mentions of mechanical, technological, or vehicular objects (e.g. television, motorbikes, camera, aeroplane, helicopters, etc.).

    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
    cluye
    -1.25
    他们的
    -1.20
     then
    -1.20
     esclavos
    -1.17
     тях
    -1.17
    CustomerId
    -1.15
     Simultaneously
    -1.09
    ȧ
    -1.08
     صفحة
    -1.08
     Fundament
    -1.06
    POSITIVE LOGITS
    idopsis
    1.45
     の
    1.20
    ј
    1.14
    <<"
    1.13
     imprime
    1.11
     objectMapper
    1.10
    槼
    1.09
    ueroa
    1.08
    zarchiwizowane
    1.07
    xane
    1.07
    Activations Density 0.172%

    No Known Activations