© 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. 34-GEMMASCOPE-RES-131K
    7. 73429
    Prev
    Next
    INDEX
    Explanations

    words starting with quasi

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

    The neuron fires on occurrences of the prefix “quasi” (e.g. in hyphenated or compound terms beginning with “quasi-”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    所以我
    -0.92
    酒屋
    -0.88
    などを
    -0.83
     oust
    -0.80
    醒来
    -0.80
    ebly
    -0.79
    atron
    -0.78
    𝟳
    -0.78
    oxidase
    -0.77
    able
    -0.77
    POSITIVE LOGITS
    為に
    0.96
     detik
    0.87
    様な
    0.86
    ᴥ
    0.82
     biex
    0.81
     quasi
    0.80
    ウター
    0.80
    弭
    0.79
     già
    0.77
     elettrica
    0.77
    Activations Density 0.017%

    No Known Activations