© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20747
    Prev
    Next
    INDEX
    Explanations

    code and testing contexts

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

    The neuron fires on code‐style argument and type‐notation tokens—especially sequences of parentheses and brackets (e.g. “(:”, “[]”, “)”) typical of function or API signatures in 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_10/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
     our
    -1.52
    </strong>
    -1.22
    峨
    -1.11
    六十
    -1.09
     will
    -1.09
     freshly
    -1.08
     kemarin
    -1.08
     yesterday
    -1.07
    。“
    -1.07
     last
    -1.06
    POSITIVE LOGITS
     тоже
    1.41
    谥
    1.40
     même
    1.34
     same
    1.34
     partecipare
    1.30
     itself
    1.29
     разных
    1.29
    一种
    1.28
    ই
    1.26
     equipamiento
    1.23
    Activations Density 0.017%

    No Known Activations