© 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. 9726
    Prev
    Next
    INDEX
    Explanations

    sequences more efficiently

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on tokens that are numeric figures (especially decimals), i.e. standalone numbers.

    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
    ในปี
    1.53
    ம்
    1.49
    س
    1.48
    在该
    1.47
    这边
    1.45
    此之外
    1.42
    在
    1.42
    在北京
    1.41
    此同时
    1.37
    在日本
    1.33
    POSITIVE LOGITS
     وفي
    2.14
     accordance
    2.11
    ا
    1.90
    quir
    1.63
    verters
    1.62
     количестве
    1.58
     vitro
    1.55
    ı
    1.55
     conjunction
    1.49
    cursion
    1.49
    Activations Density 1.521%

    No Known Activations