© 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. 5225
    Prev
    Next
    INDEX
    Explanations

    said, says, stated, read, reported

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

    The neuron specializes in detecting floating‐point numbers (tokens containing 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
    あるいは
    0.97
    阍
    0.82
    Dónde
    0.80
    ETTE
    0.79
    または
    0.76
    気を
    0.75
    রুখ
    0.75
    DAYS
    0.75
    めに
    0.75
    ﺐ
    0.74
    POSITIVE LOGITS
    .
    0.98
    .`
    0.85
    it
    0.82
    ner
    0.80
    .’
    0.80
    €.
    0.80
    ’.
    0.79
    .??
    0.71
    。
    0.71
    .'.
    0.71
    Activations Density 0.019%

    No Known Activations