© 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. 31-GEMMASCOPE-2-RES-16K
    7. 277
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric information—particularly standalone numbers and numeric expressions (including decimals and years).

    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
     solchen
    0.36
     এইরূপ
    0.35
     pueden
    0.35
    大多數
    0.35
    リ
    0.35
    場合は
    0.34
     diferite
    0.34
     নির্ভরযোগ্য
    0.33
     può
    0.32
     possono
    0.32
    POSITIVE LOGITS
     whose
    0.82
     which
    0.75
    whose
    0.73
     who
    0.72
     whom
    0.72
    which
    0.69
    ซึ่ง
    0.66
    ®,
    0.66
    ™,
    0.64
     where
    0.63
    Activations Density 4.036%

    No Known Activations