© 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. 95760
    Prev
    Next
    INDEX
    Explanations

    PHP code and API imports

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

    The neuron fires on the indefinite article “an.”

    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
     at
    -2.08
     only
    -1.86
     all
    -1.71
     on
    -1.70
     just
    -1.64
     what
    -1.63
     so
    -1.58
     their
    -1.55
     even
    -1.54
     how
    -1.46
    POSITIVE LOGITS
     escenas
    1.59
     trám
    1.58
     gän
    1.54
     unangemessene
    1.54
    Aggi
    1.52
     Partager
    1.38
     unangemess
    1.38
    튿
    1.34
     tyto
    1.34
    
    1.34
    Activations Density 0.000%

    No Known Activations