© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15152
    Prev
    Next
    INDEX
    Explanations

    Peg words

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

    The neuron strongly activates on the two‐letter prefix “Pe,” i.e. tokens at the start of words beginning with “pe.”

    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
    ↵↵
    -4.50
    -3.56
    I
    -3.13
    ro
    -2.91
    ‘
    -2.86
    se
    -2.75
    .
    -2.73
     ‘
    -2.73
     —
    -2.63
    be
    -2.59
    POSITIVE LOGITS
    
    3.23
     rajut
    3.20
    鵟
    3.09
    뿅
    3.08
    毉
    2.95
     櫃
    2.86
    because
    2.80
     parachoque
    2.78
    kemeja
    2.78
    
    2.77
    Activations Density 0.040%

    No Known Activations