© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10975
    Prev
    Next
    INDEX
    Explanations

    competitive advantage

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

    This neuron mainly fires on named entities (especially person and location names) in news‐style text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rescue
    0.60
     redemption
    0.57
    짠
    0.57
     unsuccessfully
    0.56
    arns
    0.56
     Myrtle
    0.55
    ahon
    0.54
     murky
    0.54
    勋
    0.54
     parenthesis
    0.53
    POSITIVE LOGITS
    优势
    1.47
     vantaggio
    1.32
     advantage
    1.30
     ventaja
    1.27
     vantagem
    1.24
    advantage
    1.23
     dominance
    1.16
    领先
    1.16
     dominating
    1.15
     преимуще
    1.13
    Activations Density 0.275%

    No Known Activations