© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14988
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on phrases describing saving money or other resources (e.g. “save time and money on materials and labor”).

    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
    0.82
    gen
    0.77
     phép
    0.77
     số
    0.74
     que
    0.73
    ı
    0.73
     personnes
    0.71
     locaux
    0.71
     desa
    0.71
    訪
    0.71
    POSITIVE LOGITS
    ной
    0.93
    дки
    0.81
    нова
    0.79
    тельством
    0.79
    стый
    0.78
    нца
    0.78
    ванием
    0.76
    HeaderAccept
    0.76
    وري
    0.76
     따른
    0.74
    Activations Density 0.001%

    No Known Activations