© 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. 57995
    Prev
    Next
    INDEX
    Explanations

    Wood followed by names or places

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

    The neuron consistently activates on occurrences of the token “Wood,” i.e. the surname or word “Wood” in the text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ↵
    -3.02
    歘
    -2.59
    猡
    -2.45
    ܜ
    -2.39
    秾
    -2.25
    肏
    -2.25
     hebben
    -2.20
     generó
    -2.20
     pretende
    -2.16
    爌
    -2.14
    POSITIVE LOGITS
     für
    3.17
    2
    2.63
    8
    2.42
     Now
    2.39
    5
    2.39
     για
    2.38
    1
    2.36
     Теперь
    2.36
    am
    2.33
    ;
    2.28
    Activations Density 0.005%

    No Known Activations