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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60123
    Prev
    Next
    INDEX
    Explanations

    proper nouns and abbreviations

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

    The neuron responds to long, formal noun-forming suffixes (especially “-ion”/“-ation”/“-sis”) in technical or legal text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     and
    -2.48
     or
    -2.11
     with
    -1.94
     at
    -1.78
     as
    -1.49
     when
    -1.46
     ostensibly
    -1.45
     epitom
    -1.41
     in
    -1.40
     from
    -1.38
    POSITIVE LOGITS
     dando
    1.53
    鹋
    1.46
     prato
    1.41
    spaghetti
    1.41
     nuov
    1.38
     depoz
    1.38
     tatou
    1.38
     pietre
    1.37
     fuis
    1.37
     intelek
    1.36
    Activations Density 0.019%

    No Known Activations