© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3241
    Prev
    Next
    INDEX
    Explanations

    support and services

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

    The neuron identifies occurrences of “service” (and its variants, including “services,” “SaaS,” etc.) in the 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_24_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
    s
    1.27
     parar
    1.17
     sécr
    1.12
     пищи
    1.05
     brug
    1.05
    n
    1.02
    ﺕ
    1.02
    ان
    1.01
    nesium
    1.01
     teclas
    1.00
    POSITIVE LOGITS
     SERVICES
    1.88
     Services
    1.88
     услуг
    1.66
     services
    1.64
     सर्विसेज
    1.63
     услуги
    1.61
    サービスの
    1.56
     Servicios
    1.55
     ಸಲ್ಲ
    1.55
     SERVICE
    1.54
    Activations Density 0.147%

    No Known Activations