© 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. 16084
    Prev
    Next
    INDEX
    Explanations

    either or

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

    The neuron detects strong, domain-specific action verbs in explanatory or definitional sentences (e.g. “uses,” “deletes,” “enhances”) that signal procedural or technical descriptions.

    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
     AppDelegate
    0.70
     here
    0.66
     byla
    0.64
     UNHCR
    0.64
     هنا
    0.61
     Portfolio
    0.61
     Tch
    0.61
    !
    0.61
     そして
    0.60
     здесь
    0.58
    POSITIVE LOGITS
    的一种
    0.88
    或者是
    0.83
    特定の
    0.83
    一种
    0.82
    Usually
    0.81
    एक
    0.79
     meestal
    0.79
     અથવા
    0.77
     એક
    0.77
    หรือ
    0.77
    Activations Density 0.642%

    No Known Activations