© 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. 15981
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to rare or unusually infrequent tokens (i.e. low-frequency or uncommon words).

    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
    ع
    0.86
    高端
    0.84
    ي
    0.82
    ح
    0.82
    ف
    0.81
     bleue
    0.78
    იც
    0.78
    stanbul
    0.77
     Btu
    0.77
    يال
    0.76
    POSITIVE LOGITS
    ွဲ
    0.75
    логі
    0.65
    </h3>
    0.64
    どのような
    0.63
    </h2>
    0.62
    ルの
    0.62
    IONAL
    0.62
     parametr
    0.62
    між
    0.61
    itam
    0.60
    Activations Density 0.000%

    No Known Activations