© 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. 31-GEMMASCOPE-2-RES-16K
    4. 7985
    Prev
    Next
    INDEX
    Explanations

    meaning, considering, or if

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

    This neuron fires strongly on prominent topic words or named entities that signal the main subject or focal entity of a sentence.

    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
    PATH
    0.80
    ⌥
    0.79
    Animation
    0.78
    mute
    0.73
    mard
    0.73
    CFLAGS
    0.72
    STREAM
    0.71
    و
    0.71
    dict
    0.70
     mengucapkan
    0.69
    POSITIVE LOGITS
    ung
    0.82
     crackdown
    0.82
    ungen
    0.77
     não
    0.75
    ông
    0.73
    ışt
    0.72
     tightening
    0.71
    middels
    0.71
     nå
    0.70
     हज
    0.69
    Activations Density 0.000%

    No Known Activations