© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105262
    Prev
    Next
    INDEX
    Explanations

    attributes and their values

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

    The neuron fires on identifier-like tokens used as property or attribute names (especially camel- or Pascal-cased keys) immediately before “=” in JSX, HTML/XML, and similar templating or object-literal 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
    澳门
    -1.26
    larda
    -1.16
    lardan
    -1.16
     others
    -1.09
    lnie
    -1.08
    تفسير
    -1.06
     nếu
    -1.06
     other
    -1.05
    favourites
    -1.05
    greetings
    -1.05
    POSITIVE LOGITS
     its
    1.29
     $
    1.14
     itself
    1.11
     Silla
    1.09
     traseira
    1.07
     our
    1.06
     Хотя
    1.06
    providedIn
    1.05
     fiecare
    1.05
    its
    1.04
    Activations Density 0.059%

    No Known Activations