© 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. 31-GEMMASCOPE-2-RES-16K
    7. 965
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is pick up on nonprofit‐style mission or “about us” language describing how a project was founded, its purpose, and its free or public‐service nature.

    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_31_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
    2
    0.94
    8
    0.93
    7
    0.88
    9
    0.87
    0
    0.85
     might
    0.84
    y
    0.81
    1
    0.80
    cially
    0.80
     seemingly
    0.79
    POSITIVE LOGITS
     imprescind
    1.48
     sobretudo
    1.48
     seguramente
    1.45
     imprescindible
    1.41
     realizar
    1.40
     constantemente
    1.38
     garantizar
    1.36
     sempre
    1.34
     próxim
    1.34
     aquesta
    1.34
    Activations Density 0.370%

    No Known Activations