© 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. 12983
    Prev
    Next
    INDEX
    Explanations

    potential systemic efficiency performance pathways

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

    This neuron primarily detects occurrences of the word “potential.”

    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
    er
    1.10
    en
    0.98
    or
    0.93
    ag
    0.92
    Ε
    0.91
    У
    0.89
    사람
    0.88
    沒有
    0.87
    の
    0.87
    I
    0.87
    POSITIVE LOGITS
     inconsistencies
    0.82
     sesu
    0.78
     Pathways
    0.77
    י
    0.77
    نا
    0.77
    اتی
    0.76
     suyo
    0.75
     pathways
    0.74
     espectadores
    0.74
     outliers
    0.73
    Activations Density 0.059%

    No Known Activations