© 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. 668
    Prev
    Next
    INDEX
    Explanations

    acronyms after introductory phrases

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

    The neuron fires on uppercase initialisms or acronyms (e.g. multi‐letter all-caps organization or program abbreviations).

    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
    кета
    0.45
    Ꮘ
    0.44
    жено
    0.43
     draggable
    0.42
    όμε
    0.42
    geht
    0.42
    ить
    0.42
     немає
    0.42
    zetac
    0.42
    ﮈ
    0.41
    POSITIVE LOGITS
    hereinafter
    0.69
    hereafter
    0.64
    formerly
    0.61
     hereinafter
    0.61
    which
    0.56
     popularly
    0.54
    CC
    0.52
     formerly
    0.52
    whose
    0.52
    ASTM
    0.50
    Activations Density 0.082%

    No Known Activations