© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27690
    Prev
    Next
    INDEX
    Explanations

    one of the

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

    The neuron is activated by the common superlative/distribution phrase “one of the,” i.e. it detects the “one … of the” construction.

    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
    ícias
    -1.27
    juelas
    -1.15
    vetrain
    -1.15
    ācijas
    -1.11
    orios
    -1.10
    ≯
    -1.10
    ΑΣ
    -1.07
     my
    -1.05
     decidedly
    -1.02
    OREM
    -1.02
    POSITIVE LOGITS
    ที่จะ
    1.04
     among
    1.03
    之一
    1.01
    viking
    0.98
     to
    0.98
    で一番
    0.96
    
    0.95
    jewish
    0.94
     also
    0.93
     другом
    0.92
    Activations Density 0.068%

    No Known Activations