© 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. 4149
    Prev
    Next
    INDEX
    Explanations

    high effort or high demand

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

    The neuron specifically activates on the adjective “high.”

    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
    e
    1.30
    y
    1.11
    baixo
    1.02
    et
    1.00
    yong
    0.97
    sun
    0.94
    lsen
    0.93
    lm
    0.93
    o
    0.91
     Ciò
    0.91
    POSITIVE LOGITS
     (>
    1.05
     ד
    0.92
     terroir
    0.90
    ட்சத்திர
    0.87
     δ
    0.86
     predic
    0.85
     refracting
    0.84
     cleanliness
    0.84
     vaping
    0.84
     helix
    0.83
    Activations Density 0.058%

    No Known Activations