© 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. 4681
    Prev
    Next
    INDEX
    Explanations

    social, psychological, and management principles

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

    The neuron fires strongly on technical or methodological terms—especially nouns naming processes, techniques, or research activities.

    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
     graphene
    0.76
    ɥ
    0.76
     underwhelming
    0.75
     invierno
    0.74
    tfrac
    0.72
     nochmal
    0.72
    𝚟
    0.71
     ২২
    0.71
     qPCR
    0.71
     বললো
    0.70
    POSITIVE LOGITS
     Psychological
    0.84
     organization
    0.82
     activities
    0.78
     Psychology
    0.78
     Attitudes
    0.78
     arousal
    0.77
     organizacional
    0.77
    Organiz
    0.77
    organiz
    0.77
     organizational
    0.76
    Activations Density 0.212%

    No Known Activations