© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70789
    Prev
    Next
    INDEX
    Explanations

    secondary classifier for nouns

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

    The neuron specifically fires on occurrences of the word “secondary.”

    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
    絢
    -1.26
     But
    -1.25
    vedades
    -1.24
     There
    -1.23
     sería
    -1.18
    यं
    -1.14
     It
    -1.13
     showing
    -1.11
     народу
    -1.11
     discernible
    -1.09
    POSITIVE LOGITS
    secondary
    1.94
    Secondary
    1.82
     secondary
    1.75
     sekund
    1.75
     Secondary
    1.63
     SECONDARY
    1.58
    primary
    1.40
    warten
    1.38
    SECONDARY
    1.37
     secondaires
    1.36
    Activations Density 0.086%

    No Known Activations