© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8847
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on low‐frequency or unusual tokens—things like rare words, proper names, long/complex strings, and other atypical vocabulary.

    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_31_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
    ,
    0.93
    ed
    0.88
    ing
    0.84
    _
    0.84
    er
    0.83
    -
    0.81
    el
    0.81
    ic
    0.80
    et
    0.77
    at
    0.75
    POSITIVE LOGITS
    Loksatta
    0.91
     pandémie
    0.91
     réforme
    0.87
    𝒾
    0.85
     Música
    0.85
     musique
    0.84
    𝚖
    0.84
     música
    0.83
     Londra
    0.83
    Cómo
    0.83
    Activations Density 0.000%

    No Known Activations