© 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. 32726
    Prev
    Next
    INDEX
    Explanations

    parts of words followed by specific suffixes

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

    The neuron activates on subword stems that carry core content—i.e. the root morphemes of meaningful nouns and adjectives (like “folded,” “degrad,” “carnivor,” “glyco,” etc.).

    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
    に行って
    -1.23
    árbol
    -1.09
     niitä
    -1.08
    iato
    -1.04
     tää
    -1.02
    หรือ
    -1.00
    tanian
    -1.00
     někdo
    -1.00
     quedaron
    -1.00
    좋
    -0.99
    POSITIVE LOGITS
    il
    1.04
    瞟
    1.03
     Utama
    1.00
    もしろ
    0.98
    astic
    0.98
     Tarif
    0.96
     Warga
    0.95
    oria
    0.92
    amo
    0.91
    ienia
    0.91
    Activations Density 0.087%

    No Known Activations