© 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. 74362
    Prev
    Next
    INDEX
    Explanations

    plural nouns

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

    The neuron selectively activates on longer word stems or multi‐character substrings (i.e. medium-length fragments) rather than on short common tokens.

    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
     to
    -2.56
     they
    -1.71
     about
    -1.63
    ("")){
    -1.51
    ,”
    -1.49
    jbl
    -1.49
    dne
    -1.48
     what
    -1.47
    licazione
    -1.47
     principalmente
    -1.45
    POSITIVE LOGITS
     this
    1.93
    Дмитрий
    1.79
    Namun
    1.73
    Meski
    1.72
    Отзыв
    1.71
    Sedangkan
    1.70
    Андрей
    1.68
    Tetapi
    1.68
    Kedua
    1.67
    Bahkan
    1.66
    Activations Density 0.313%

    No Known Activations