© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92266
    Prev
    Next
    INDEX
    Explanations

    laminin, laminitis, Lagos, latent

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

    The neuron detects occurrences of the substring “lamin” (e.g. in “laminin,” “lamina,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ถ้า
    -1.34
     不锈钢
    -1.34
     attivo
    -1.34
    ੮
    -1.32
     industriale
    -1.31
    铪
    -1.30
    瓘
    -1.29
    XICO
    -1.27
     parlar
    -1.27
     sentimento
    -1.27
    POSITIVE LOGITS
     как
    1.26
    </b>
    1.25
    (){
    1.17
     ev
    1.15
     credence
    1.10
     pretend
    1.09
    PA
    1.09
    izations
    1.07
     kicks
    1.06
    \
    1.05
    Activations Density 0.057%

    No Known Activations