© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45376
    Prev
    Next
    INDEX
    Explanations

    words starting with sp

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

    The neuron strongly activates on the two-letter subword “sp” wherever it appears within words.

    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
    )”
    -2.89
    )’
    -2.64
    輊
    -2.59
    in
    -2.53
    ᨈ
    -2.47
    骓
    -2.45
    >");
    -2.42
    …”
    -2.39
    鏨
    -2.38
    ….”
    -2.34
    POSITIVE LOGITS
    ?"
    3.75
    ৢ
    2.63
     '
    2.50
    笑笑
    2.48
    ...?
    2.47
    。"
    2.33
    3
    2.33
    2
    2.31
     --
    2.27
    tedì
    2.27
    Activations Density 0.013%

    No Known Activations