© 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. 7964
    Prev
    Next
    INDEX
    Explanations

    informal greetings and expressions

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

    This neuron strongly activates on sentence‐ending punctuation (periods) that mark the end of posts or sentences.

    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
     PFAS
    1.35
     ২০২৩
    1.34
     ২০২২
    1.34
     २०२
    1.33
     २०२२
    1.29
     Covid
    1.21
    🫣
    1.21
    🥰
    1.16
     🥰
    1.16
     ChatGPT
    1.10
    POSITIVE LOGITS
     :/
    1.21
     =)
    1.13
     xD
    1.11
    Haha
    1.08
    http
    1.06
     :]
    1.05
     haha
    1.03
    ♥
    1.02
     http
    1.00
    (:
    0.98
    Activations Density 0.288%

    No Known Activations