© 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. 11949
    Prev
    Next
    INDEX
    Explanations

    articles and determiners in many languages

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

    This neuron detects numeric tokens that represent floating‐point numbers (i.e. multi‐digit numbers with a decimal point).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the phrase "put off" or variations of phrases with "put" followed by directional words like "out", "forth", or "behind".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    adverbial particles in phrasal verb constructions, especially directional/completive particles following a verb.

    oai_token-act-pair · gpt-5Triggered 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
    createdAt
    0.36
    ϲ
    0.35
    쌩
    0.34
    llllll
    0.34
    Ông
    0.34
    Waar
    0.33
    زاده
    0.33
     kullanarak
    0.32
    在了
    0.32
    esth
    0.32
    POSITIVE LOGITS
     a
    0.72
     an
    0.70
     ஒரு
    0.62
     μια
    0.52
     isang
    0.50
     một
    0.50
     а
    0.50
    一个
    0.50
     një
    0.50
     એક
    0.48
    Activations Density 0.000%

    No Known Activations