© 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. 127723
    Prev
    Next
    INDEX
    Explanations

    The neuron preferentially fires on mid‐frequency, content‐bearing tokens (e.g. longer nouns, verbs, proper names) and punctuation rather than on very common function words.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    És
    -1.02
    miesz
    -0.94
     OMIT
    -0.91
    іга
    -0.88
    ⛩
    -0.87
    σιμοποι
    -0.86
     chocs
    -0.82
    cotta
    -0.82
     efekty
    -0.82
     preta
    -0.81
    POSITIVE LOGITS
     basado
    0.91
     iniciar
    0.83
     denuncias
    0.82
     xi
    0.81
     prolong
    0.81
     fanden
    0.81
     unserem
    0.80
     cuz
    0.80
    足を
    0.79
     trigger
    0.78
    Activations Density 0.088%

    No Known Activations