© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2591
    Prev
    Next
    INDEX
    Explanations

    acronyms and their meanings

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

    The neuron strongly activates on multi‐word named entities—especially sequences of capitalized words like brand names, organization names, acronyms, and slogans.

    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
     frescoes
    0.64
    ᥒ
    0.62
    rctx
    0.60
    етесь
    0.57
    ጇ
    0.57
    Poems
    0.57
    dispatchEvent
    0.56
    akuza
    0.55
     勺
    0.55
    賭
    0.55
    POSITIVE LOGITS
     acronym
    1.13
     abbreviation
    0.78
     initials
    0.63
    édération
    0.61
     structured
    0.60
     abbreviations
    0.60
     F
    0.58
     identification
    0.58
     siglas
    0.58
     facilitator
    0.57
    Activations Density 0.163%

    No Known Activations