© 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. 5034
    Prev
    Next
    INDEX
    Explanations

    followed by

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

    The neuron activates on verbs that link or combine items—particularly those introducing accompaniment or sequence (e.g. “complemented by,” “mixed with,” “followed by,” “combined with”).

    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
     solely
    0.74
    orin
    0.70
     museums
    0.70
    ългар
    0.65
    ध्यक्ष
    0.64
    ופן
    0.64
     primarily
    0.63
    ={\
    0.63
     airplanes
    0.63
     सिंपली
    0.63
    POSITIVE LOGITS
     ditambah
    0.94
     последу
    0.82
    然后
    0.82
    其它
    0.81
     তারপর
    0.80
    তারপর
    0.79
     потім
    0.78
     약간
    0.75
     나머지
    0.75
     Then
    0.74
    Activations Density 0.223%

    No Known Activations