© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8489
    Prev
    Next
    INDEX
    Explanations

    buoyancy control and dopamine

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

    specialized technical terms across different fields like radiation, contactless technology, buoyancy, and dopamine.

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

    This neuron fires on words that carry common English derivational suffixes (–ant, –ance, –ment, –ancy, –less), i.e. technical or formal terms formed by those endings.

    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
    er
    -2.88
    </b>
    -2.78
    derdag
    -2.70
     العملية
    -2.61
     schwier
    -2.53
    enterOuterAlt
    -2.53
    š
    -2.44
    鉭
    -2.36
    o
    -2.34
    section
    -2.33
    POSITIVE LOGITS
    觧
    3.08
    蒾
    2.98
    苼
    2.98
    祧
    2.97
    汭
    2.92
    </h3>
    2.72
    遹
    2.67
    鹩
    2.63
    تیجه
    2.61
    雰
    2.56
    Activations Density 0.005%

    No Known Activations