© 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. 11379
    Prev
    Next
    INDEX
    Explanations

    What is

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

    The neuron fires on prominent section‐heading or topic phrases—i.e. the main subject titles or labels that introduce a new segment.

    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
     without
    0.68
     Sans
    0.59
    excluding
    0.58
     Vial
    0.57
     Acceleration
    0.57
     with
    0.57
     MATHEMAT
    0.57
     D
    0.55
     excluding
    0.55
    without
    0.54
    POSITIVE LOGITS
    是一種
    1.28
    是一個
    1.22
    是一种
    1.21
    是一个
    1.04
    是一家
    0.95
     является
    0.93
    是一位
    0.91
     là
    0.89
     adalah
    0.89
    是一款
    0.89
    Activations Density 0.140%

    No Known Activations