© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68620
    Prev
    Next
    INDEX
    Explanations

    abstract nouns followed by definitions

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

    The neuron fires on the nominal-definitional pattern in explanatory sentences—e.g. “X is the Y of Z,” highlighting words like “occurrence of,” “process of,” “act of,” etc.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     already
    -1.21
    inverno
    -1.20
     they
    -1.16
    :
    -1.15
     it
    -1.13
     have
    -1.11
     اللجنة
    -1.05
     again
    -1.01
     please
    -1.01
    倣
    -0.96
    POSITIVE LOGITS
     tillegg
    1.38
    周泽
    1.16
    quando
    1.16
     mineures
    1.15
    Sementara
    1.13
    Namun
    1.13
     الذي
    1.10
     ambayo
    1.10
    Sedangkan
    1.09
    懾
    1.09
    Activations Density 0.065%

    No Known Activations