© 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. 15276
    Prev
    Next
    INDEX
    Explanations

    The neuron specifically responds to the word “main,” especially when it’s used as the modifier in “main + noun” phrases.

    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
    ায়ার
    1.05
    新
    1.05
    இந்த
    1.05
     tasted
    1.04
     giorni
    1.02
    ਤਾ
    1.02
    が多く
    1.02
    铀
    1.02
     prioritization
    1.01
    른
    1.00
    POSITIVE LOGITS
    テナンス
    1.66
    stays
    1.42
    nnet
    1.16
    ции
    1.05
    ių
    1.03
    сць
    1.02
     reds
    1.01
    నే
    1.00
    tained
    0.96
     rivets
    0.95
    Activations Density 0.033%

    No Known Activations