© 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. 98266
    Prev
    Next
    INDEX
    Explanations

    list, update, enable, cleaning, cancel

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

    The neuron fires on structural code‐block boundary markers—e.g. closing braces, fence ticks, and similar punctuation that delimit chunks of code.

    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
     autocollant
    -1.00
     войск
    -0.98
     Aceite
    -0.95
     Derechos
    -0.94
     píše
    -0.91
    ЦИ
    -0.91
    崧
    -0.91
     Recursos
    -0.90
     plainte
    -0.89
     znaczy
    -0.88
    POSITIVE LOGITS
    is
    0.96
    we
    0.93
    on
    0.91
    so
    0.88
    or
    0.87
    po
    0.87
    u
    0.87
    j
    0.83
    d
    0.83
    de
    0.82
    Activations Density 0.006%

    No Known Activations