© 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. 661
    Prev
    Next
    INDEX
    Explanations

    foundry, footprint, overruns, hotlines

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

    The neuron is triggered by uncommon, domain-specific tokens—particularly capitalized headings, acronyms, or technical terms—rather than ordinary words.

    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
    的に
    0.68
    रीबन
    0.66
    inairement
    0.64
    avelmente
    0.63
    olojik
    0.63
    attamente
    0.62
    𝚓
    0.62
    ubercul
    0.61
     chromed
    0.61
    olutamente
    0.61
    POSITIVE LOGITS
     Advisory
    0.62
     Ltd
    0.61
     Bennett
    0.57
     Center
    0.57
    manship
    0.55
     Realty
    0.55
     &
    0.54
     Affairs
    0.53
     Invitational
    0.53
     Handbook
    0.52
    Activations Density 0.414%

    No Known Activations