© 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. 119408
    Prev
    Next
    INDEX
    Explanations

    free followed by a noun

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

    The neuron fires whenever it sees the token “free” (including in compounds like “free‐standing” or “free of charge”).

    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
     “
    -3.17
    \
    -3.03
     they
    -3.03
     
    -2.94
    ar
    -2.78
     to
    -2.73
     superb
    -2.66
     presentan
    -2.66
    
    -2.64
     terrific
    -2.58
    POSITIVE LOGITS
    酲
    3.31
    Despite
    3.30
    𖡼
    3.23
     bahwa
    3.13
     放題
    2.97
    0
    2.97
     baumwolle
    2.84
    Even
    2.84
     間取り
    2.83
    While
    2.80
    Activations Density 0.049%

    No Known Activations