© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 1566
    Prev
    Next
    INDEX
    Explanations

    identifying and developing solutions

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

    The neuron fires strongly on occurrences of the verb “develop” (in its various forms) and other closely related action verbs describing the creation or planning of strategies and programs.

    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
     only
    0.79
     केवल
    0.77
    いた
    0.76
    ทั้งหมด
    0.75
    อาจ
    0.72
    ทั้ง
    0.71
    แค่
    0.71
     iPhone
    0.70
    อะไร
    0.68
     hanya
    0.67
    POSITIVE LOGITS
     ומ
    0.89
     ਅਤੇ
    0.87
     અને
    0.82
     και
    0.80
     ও
    0.77
     and
    0.77
     এবং
    0.77
     ಮತ್ತು
    0.77
     và
    0.76
     आणि
    0.76
    Activations Density 0.012%

    No Known Activations