© 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. 10736
    Prev
    Next
    INDEX
    Explanations

    following punctuation

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

    The neuron primarily detects sentence-ending boundaries (i.e. the closing punctuation that marks the end of a sentence).

    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
    Asimismo
    1.28
    Moreover
    1.12
    此外
    1.08
     asimismo
    1.02
     посредством
    0.97
    Owing
    0.93
     Asimismo
    0.91
    Ḥ
    0.91
    Ṣ
    0.90
     gemäß
    0.88
    POSITIVE LOGITS
     alot
    1.15
     things
    1.08
     가지고
    1.02
     엄청
    1.00
     freaking
    1.00
     really
    0.99
     সেটা
    0.98
     俺
    0.97
     tane
    0.96
     gets
    0.95
    Activations Density 0.340%

    No Known Activations