© 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. 13007
    Prev
    Next
    INDEX
    Explanations

    text examples

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

    This neuron fires on descriptive, abundance‐style terms in fashion trend write‐ups—i.e. words and phrasings that emphasize how ubiquitous or “everywhere” certain design features are.

    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
    USSR
    0.66
     inhom
    0.61
    --
    0.59
    /
    0.55
    사
    0.55
     homogenous
    0.54
    5
    0.54
    4
    0.53
     통해서
    0.52
     amplio
    0.51
    POSITIVE LOGITS
    ısını
    0.75
     SmackDown
    0.69
     でしょう
    0.68
    ríklad
    0.66
    ⁤
    0.66
    poruč
    0.66
     Букмекерская
    0.65
    ější
    0.64
    َّ
    0.63
     приблизи
    0.61
    Activations Density 1.682%

    No Known Activations