© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14687
    Prev
    Next
    INDEX
    Explanations

    years ago

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

    The neuron strongly fires on numeric tokens representing years or time spans (e.g. floating-point “years” values).

    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
    رل
    0.69
     poblaciones
    0.66
    拃
    0.63
    hattam
    0.62
     Planet
    0.60
    κολ
    0.60
     लगातार
    0.59
    ческим
    0.59
     Familien
    0.59
    ustrated
    0.59
    POSITIVE LOGITS
    소
    0.77
     ago
    0.74
    ما
    0.66
     geleden
    0.64
    说
    0.64
    แต่ง
    0.62
    дів
    0.62
    ва
    0.61
    อิ
    0.60
     antise
    0.60
    Activations Density 0.036%

    No Known Activations