© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7069
    Prev
    Next
    INDEX
    Explanations

    This neuron detects agent nouns—words denoting a person or thing that performs an action—typically ending in “-er” or “-or.”

    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
    י
    1.47
    те
    1.26
    ва
    1.25
    ي
    1.19
    𝐝
    1.19
    ्स
    1.18
    にい
    1.17
    یی
    1.13
    ला
    1.12
    ве
    1.12
    POSITIVE LOGITS
     extraordinaire
    1.47
    械
    1.13
    ‍♂️
    1.07
    ‍♀️
    1.02
    ’
    0.95
    </sup>
    0.88
     paradox
    0.88
    們
    0.86
     Stat
    0.86
     proviso
    0.85
    Activations Density 2.922%

    No Known Activations