© 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. 16130
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to detect ordinal date suffixes (e.g. the “th” in “7th,” “18th,” etc.)

    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
    婿
    0.82
     croissant
    0.78
     VAL
    0.77
     gourmet
    0.77
    周期
    0.76
    کرد
    0.74
     CNA
    0.74
     STRA
    0.73
     combo
    0.73
     smoothie
    0.73
    POSITIVE LOGITS
     menilai
    0.85
     nieruch
    0.85
    ],
    0.80
    neho
    0.79
     czyli
    0.77
    धिका
    0.75
    olazione
    0.75
    檎
    0.74
    ſon
    0.74
    localVarHTTP
    0.73
    Activations Density 0.001%

    No Known Activations