© 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. 22-GEMMASCOPE-RES-131K
    7. 64324
    Prev
    Next
    INDEX
    Explanations

    CURRENT OFFER

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

    The neuron detects isolated punctuation or special-symbol tokens (e.g. semicolons, asterisks, greater‐than signs) rather than letters or words.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     inaugura
    -1.48
     Bélgica
    -1.45
    ICALLY
    -1.38
     monstruos
    -1.37
     investiga
    -1.35
     Dinamarca
    -1.33
     tiros
    -1.32
     bebek
    -1.32
    acterísticas
    -1.27
     hırka
    -1.27
    POSITIVE LOGITS
    )
    1.91
    s
    1.75
    i
    1.62
    ,
    1.55
    I
    1.52
    !
    1.52
    t
    1.50
    n
    1.49
    e
    1.47
    a
    1.44
    Activations Density 0.001%

    No Known Activations