© 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. 13921
    Prev
    Next
    INDEX
    Explanations

    there is/are

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

    The neuron is keyed to detect the token “there.”

    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
    니아
    0.91
     caveat
    0.90
    /
    0.88
     historic
    0.81
    sand
    0.79
     world
    0.79
     outlying
    0.78
     NASA
    0.78
    ™
    0.78
     Berkeley
    0.77
    POSITIVE LOGITS
    abouts
    1.05
    лі
    1.00
     അവിടെ
    0.98
    ود
    0.95
    のリ
    0.93
     немає
    0.91
     υπάρχ
    0.90
    ня
    0.89
    podob
    0.89
    ون
    0.88
    Activations Density 0.028%

    No Known Activations