© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129920
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on specialized domain-specific technical terms and abbreviations (e.g. proper nouns, acronyms, and jargon).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mapping to criteria or categories

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Garantie
    -1.28
    牡蠣
    -1.19
    焢
    -1.16
    というわけで
    -1.13
    Kegiatan
    -1.08
    peka
    -1.05
    Programma
    -1.05
    Beberapa
    -1.05
     табле
    -1.02
     proč
    -1.02
    POSITIVE LOGITS
     equivalent
    1.21
    L
    1.15
     corresponding
    1.05
     "
    1.02
     sogen
    1.00
     entspre
    0.99
    C
    0.95
    D
    0.95
    an
    0.95
     guter
    0.95
    Activations Density 0.138%

    No Known Activations