© 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. 7733
    Prev
    Next
    INDEX
    Explanations

    application or applications

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

    The neuron fires on words that describe how a product or system is used or applied (e.g. usage/application contexts).

    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
     the
    -1.69
     内衣
    -1.66
     to
    -1.55
    ského
    -1.42
     It
    -1.41
     素描
    -1.39
     休閒
    -1.38
     from
    -1.37
     they
    -1.33
     reuni
    -1.33
    POSITIVE LOGITS
    6
    1.52
     celles
    1.47
    岀
    1.43
    3
    1.38
    9
    1.34
    های
    1.33
    in
    1.32
    4
    1.32
    if
    1.30
    those
    1.30
    Activations Density 0.044%

    No Known Activations