© 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. 9694
    Prev
    Next
    INDEX
    Explanations

    code, scripts, and mathematical notation

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

    This neuron activates on unusually long tokens (lengthy or technical words).

    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
     kysy
    -1.06
    Läh
    -1.02
     pojaw
    -1.01
    帳に追加
    -1.00
    ਗ਼
    -0.99
    身近
    -0.99
     Fähig
    -0.97
    italy
    -0.96
     saveurs
    -0.96
     lidí
    -0.94
    POSITIVE LOGITS
    ....
    0.94
    return
    0.91
    ❉
    0.86
     both
    0.84
     centrifuge
    0.83
    幟
    0.80
    tembro
    0.80
     Wiesen
    0.79
    address
    0.79
    ........
    0.78
    Activations Density 0.052%

    No Known Activations