© 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. 24-GEMMASCOPE-2-RES-16K
    7. 13592
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to unusually long tokens—i.e. words of greater length.

    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
     दुसऱ्या
    0.86
    牷
    0.85
     ಅದ
    0.81
     그러
    0.80
     заболеваний
    0.79
     Ні
    0.78
    𝒟
    0.77
     Terbaik
    0.76
    rumah
    0.75
    İR
    0.75
    POSITIVE LOGITS
    in
    0.96
    en
    0.95
    at
    0.86
    ar
    0.83
    ed
    0.83
    is
    0.82
    ia
    0.82
    es
    0.81
    ored
    0.80
    í
    0.78
    Activations Density 0.000%

    No Known Activations