© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9042
    Prev
    Next
    INDEX
    Explanations

    what i am doing

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

    The neuron fires strongly on present‐participle (“-ing”) verbs—most prominently “doing” but also verbs like “thinking,” “working,” or “pretending.”

    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
     melalui
    -1.78
     both
    -1.73
     what
    -1.66
     one
    -1.63
     acondicionado
    -1.58
     elástico
    -1.57
     και
    -1.56
     energético
    -1.56
     also
    -1.54
     fotográfica
    -1.51
    POSITIVE LOGITS
     in
    1.83
    chenen
    1.48
     NORMAL
    1.38
     solide
    1.36
    频繁
    1.36
     which
    1.35
    venant
    1.33
     ema
    1.31
     gitt
    1.26
     Câ
    1.24
    Activations Density 0.009%

    No Known Activations