© 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. 7452
    Prev
    Next
    INDEX
    Explanations

    on followed by other words

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

    This neuron is primarily detecting the preposition “on,” especially when it appears in temporal or locative contexts.

    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
    rave
    0.59
    Hon
    0.54
    实话
    0.54
     Hon
    0.51
    ldr
    0.51
    cleanup
    0.51
     فورم
    0.50
    耒
    0.50
    backup
    0.49
    Consent
    0.49
    POSITIVE LOGITS
     topography
    0.62
     ग्री
    0.57
    otopic
    0.55
    כות
    0.55
     পরিষে
    0.55
     демо
    0.54
     метод
    0.54
     erupt
    0.54
     請
    0.54
     dém
    0.53
    Activations Density 0.004%

    No Known Activations