© 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. 59889
    Prev
    Next
    INDEX
    Explanations

    talking aboutworrying about

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

    The neuron fires on verbs or adjectives that are typically followed by the preposition “about” (e.g. passionate, worry, forget, learn, talk, care).

    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
     regarding
    -2.42
     Regarding
    -2.03
     concerning
    -2.03
    regarding
    -1.99
    Regarding
    -1.97
     Concerning
    -1.81
    Concerning
    -1.77
     concernant
    -1.48
    關於
    -1.48
    concer
    -1.46
    POSITIVE LOGITS
     небольшой
    1.00
     asistentes
    0.94
    咵
    0.90
    IFUL
    0.86
     bocetos
    0.86
     obreros
    0.85
     alemanes
    0.85
     speciale
    0.84
     meisjes
    0.83
     unſ
    0.83
    Activations Density 0.063%

    No Known Activations