© 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. 22-GEMMASCOPE-RES-131K
    7. 104540
    Prev
    Next
    INDEX
    Explanations

    domain and regions

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

    The neuron fires on mathematical discussion of domains (and related concepts like convergence/regions) in formal math expressions.

    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
     Bakterien
    -1.05
     náš
    -1.02
     noong
    -0.91
    maler
    -0.89
     racconta
    -0.89
    leftarrow
    -0.88
    になり
    -0.87
    靭
    -0.87
     privada
    -0.86
     our
    -0.86
    POSITIVE LOGITS
     любые
    0.97
    матика
    0.94
     precau
    0.92
     restitu
    0.91
     expor
    0.90
     acep
    0.90
    olin
    0.90
    pueden
    0.90
     bolos
    0.90
    vaila
    0.90
    Activations Density 0.033%

    No Known Activations