© 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. 72349
    Prev
    Next
    INDEX
    Explanations

    close association and connection

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

    The neuron is specifically triggered by occurrences of the adverb “closely.”

    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
     of
    -2.81
     andere
    -2.36
    sistors
    -2.28
     Unless
    -2.23
     discrepancy
    -2.22
    餮
    -2.20
     eigentliche
    -2.20
     OTHER
    -2.20
    ⬈
    -2.19
    籥
    -2.19
    POSITIVE LOGITS
    n
    3.77
    re
    3.39
    ll
    3.22
    f
    3.22
    t
    3.08
    an
    2.86
    s
    2.81
    to
    2.69
     sehingga
    2.69
     эту
    2.63
    Activations Density 0.004%

    No Known Activations