© 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. 21172
    Prev
    Next
    INDEX
    Explanations

    how something is done or its degree

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

    The neuron strongly activates on the word “how.”

    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
     for
    -1.88
     Japão
    -1.47
    
    -1.47
     penerbangan
    -1.47
     addition
    -1.46
     there
    -1.41
     in
    -1.40
     kerjasama
    -1.39
     jät
    -1.39
     CiNii
    -1.36
    POSITIVE LOGITS
    ्ड
    1.44
     geel
    1.43
     alimentar
    1.38
     productivo
    1.38
     his
    1.38
     laag
    1.33
     hulle
    1.30
     دیگران
    1.26
     logements
    1.22
    だけは
    1.22
    Activations Density 0.009%

    No Known Activations