© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10253
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on ordinal‐suffix tokens (e.g. “74th,” “72nd,” 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
    IVES
    0.78
     reaches
    0.76
     impuls
    0.75
     crosses
    0.73
    D
    0.73
    F
    0.72
     rises
    0.72
    HN
    0.71
    BIN
    0.71
    m
    0.71
    POSITIVE LOGITS
    ぴ
    0.82
     órg
    0.80
    opcao
    0.79
     arquitet
    0.77
     অপর্ণ
    0.75
    ؟!
    0.75
    ្ឋ
    0.73
    planilla
    0.73
     Потом
    0.73
    ...";
    0.72
    Activations Density 0.000%

    No Known Activations