© 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. 7884
    Prev
    Next
    INDEX
    Explanations

    an followed by a word

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

    The neuron detects floating‐point numeric tokens (numbers with digits and a decimal point).

    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
    ing
    1.34
     fleste
    1.30
    ೆ
    1.28
    ை
    1.27
     ความ
    1.23
    oires
    1.22
    a
    1.22
    }=\
    1.14
    ść
    1.14
    客様
    1.13
    POSITIVE LOGITS
    ন
    1.47
    תי
    1.45
    িক
    1.40
    ق
    1.40
    ן
    1.36
    r
    1.29
    ر
    1.26
    tegr
    1.20
     extremity
    1.18
     assortment
    1.17
    Activations Density 0.267%

    No Known Activations