© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11592
    Prev
    Next
    INDEX
    Explanations

    result in additional

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

    This neuron fires on words that signal repeated or sequential actions or time intervals (e.g. “following,” “requests,” “again,” “day,” “year”).

    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
    fact
    0.64
    ভেজ
    0.64
    蹒
    0.63
    sixth
    0.62
    conform
    0.61
    ccess
    0.59
    intre
    0.59
    빙
    0.59
    착
    0.58
    સ્ટ
    0.57
    POSITIVE LOGITS
     sender
    0.64
     FEDERAL
    0.62
    INCLUDE
    0.55
     ВК
    0.54
     AW
    0.53
    នា
    0.53
     Quezon
    0.53
     جمہوری
    0.52
    θε
    0.52
     collective
    0.50
    Activations Density 0.000%

    No Known Activations