© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14802
    Prev
    Next
    INDEX
    Explanations

    sense experience followed by perception

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

    This neuron responds to words describing sensory experiences or bodily sensations (e.g., hearing, smelling, touching, feeling).

    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
     الجمهور
    0.78
     terenie
    0.78
     decked
    0.75
    ủi
    0.73
    骥
    0.73
    局面
    0.72
     দলের
    0.72
     문제를
    0.71
    訕
    0.71
     থাকলেও
    0.71
    POSITIVE LOGITS
     vibrations
    1.27
     lembut
    1.25
     inhale
    1.09
     inhalation
    1.05
     ripples
    1.05
     textura
    1.05
     sonidos
    1.05
     exhale
    1.05
     texture
    1.03
     textures
    1.03
    Activations Density 1.847%

    No Known Activations