© 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. 14941
    Prev
    Next
    INDEX
    Explanations

    purposes only / educational / informational

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

    The neuron strongly activates on very common English function words (e.g. “for,” “the,” “a,” “this,” “some,” “that”).

    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
    จากการ
    0.80
     тщательно
    0.72
    らか
    0.69
    eds
    0.68
     kdy
    0.68
    ﻟ
    0.68
    く
    0.67
    averaged
    0.66
    6
    0.66
     torno
    0.65
    POSITIVE LOGITS
     purposes
    1.95
     sake
    1.61
     Purposes
    1.59
     Sake
    1.42
    来说
    1.24
     awhile
    1.16
     reasons
    1.15
    giveness
    1.13
     betterment
    1.06
     starters
    0.99
    Activations Density 0.676%

    No Known Activations