© 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. 2953
    Prev
    Next
    INDEX
    Explanations

    levothyroxine, measures, cap

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

    The neuron reliably fires on technical/mechanical terms referring to tools, machines, engines, or their components.

    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
    8
    0.87
    9
    0.82
     American
    0.80
    6
    0.78
     September
    0.77
     July
    0.76
    3
    0.73
    4
    0.72
    American
    0.69
     likely
    0.69
    POSITIVE LOGITS
     constantemente
    0.86
    🫣
    0.84
     suelen
    0.83
     constantes
    0.80
    🫢
    0.80
    🤩
    0.79
    🤭
    0.79
    🥹
    0.79
    だけでなく
    0.78
     hidrat
    0.77
    Activations Density 0.913%

    No Known Activations