© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7391
    Prev
    Next
    INDEX
    Explanations

    directional geographical locations

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

    The neuron fires on compass-direction adjectives (e.g. northeastern, western, southeastern, southern) used to describe locations.

    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
     morals
    0.64
    ’
    0.60
     toate
    0.59
    '
    0.58
    .
    0.58
     alle
    0.57
     todas
    0.57
    andre
    0.57
     muitas
    0.55
    的事情
    0.54
    POSITIVE LOGITS
     قاسمی
    0.64
     известно
    0.61
    γο
    0.61
    рья
    0.61
    <unused38>
    0.59
     पेड़
    0.57
    лё
    0.57
    pli
    0.57
    лих
    0.57
    یں
    0.56
    Activations Density 0.000%

    No Known Activations