© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8143
    Prev
    Next
    INDEX
    Explanations

    dopaminergic

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

    words ending in "ergic" that relate to neurotransmitter systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively responds to technical terms ending in “-ergic” (i.e. names of neurotransmitter/receptor systems).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    E
    -2.97
    2
    -2.94
    P
    -2.52
    1
    -2.41
    对
    -2.38
    くらい
    -2.31
    大多
    -2.28
    It
    -2.23
     красивый
    -2.17
     cuya
    -2.16
    POSITIVE LOGITS
    攆
    2.78
    )]
    2.72
    }
    2.70
    </h3>
    2.67
    ization
    2.64
    鲀
    2.58
    enablog
    2.56
    },
    2.56
    鉝
    2.56
    ⢅
    2.53
    Activations Density 0.014%

    No Known Activations