© 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. 22-GEMMASCOPE-RES-131K
    7. 38993
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    The neuron fires strongly on sensational, clickbait‐style headline phrasing (e.g. “Stop the insanity,” “using the same methods,” “one weird trick,” “shop now,” “what …”).

    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
    <b>
    -1.23
     suí
    -1.11
    事で
    -1.10
     brilhante
    -1.10
    ↵↵
    -1.10
     abstrato
    -1.09
    向けの
    -1.02
     feminino
    -1.01
    世界上
    -1.00
    ))+
    -1.00
    POSITIVE LOGITS
     proverbial
    1.16
    دانلود
    1.02
    AMENTO
    0.98
    參考文獻
    0.98
    などを
    0.96
     penanganan
    0.96
    了许多
    0.95
     victime
    0.94
     poussière
    0.94
    āja
    0.94
    Activations Density 0.076%

    No Known Activations