© 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. 1250
    Prev
    Next
    INDEX
    Explanations

    locations or references 'here'

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

    The neuron specifically fires on the deictic adverb “here.”

    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
    ს
    0.84
    ➢
    0.82
    ۔
    0.80
    פ
    0.79
    מ
    0.76
    Após
    0.73
    𝘀
    0.73
    OTTOM
    0.72
     đem
    0.71
    ς
    0.71
    POSITIVE LOGITS
    abouts
    1.01
    here
    0.91
     وهنا
    0.91
    fordshire
    0.76
    itable
    0.75
    il
    0.73
    lə
    0.72
    umption
    0.71
    inement
    0.70
    durch
    0.70
    Activations Density 0.069%

    No Known Activations