© 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. 128796
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting very high‐frequency “stop” words (common function words and basic verbs/adverbs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    state endings or ongoing conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ENOUGH
    -0.98
     possibles
    -0.90
     bagay
    -0.87
     FMI
    -0.87
     takut
    -0.83
     POI
    -0.79
     aristocrat
    -0.78
     hak
    -0.77
     unif
    -0.76
     pomodoro
    -0.76
    POSITIVE LOGITS
     Características
    0.98
    柠
    0.97
     فراهم
    0.96
     llegará
    0.95
     ganhou
    0.94
    cepatan
    0.91
     period
    0.91
    moments
    0.90
     passed
    0.90
    ähän
    0.88
    Activations Density 0.069%

    No Known Activations