© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 735
    Prev
    Next
    INDEX
    Explanations

    This neuron responds strongly to capitalized terms and acronyms (proper nouns and initialisms).

    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
    Bu
    0.46
    President
    0.45
     പൂ
    0.45
    Jefferson
    0.45
    它
    0.45
     President
    0.44
    Alcohol
    0.44
    四年
    0.44
    孙
    0.44
    俢
    0.44
    POSITIVE LOGITS
     alike
    0.95
    それぞれ
    0.91
     jeweils
    0.91
     respectively
    0.86
     respectivement
    0.86
     respectivamente
    0.78
     각각
    0.78
    いずれ
    0.77
     ஆகிய
    0.75
    respectively
    0.74
    Activations Density 0.027%

    No Known Activations