© 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. 10-GEMMASCOPE-RES-131K
    7. 99715
    Prev
    Next
    INDEX
    Explanations

    receptors and activity

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

    The neuron detects the term "immunoreactivity" in scientific papers about neurobiology and biochemistry.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    </b>
    -3.50
    糶
    -2.61
     и
    -2.39
     Для
    -2.36
     цей
    -2.30
    ة
    -2.28
    n
    -2.27
     To
    -2.27
    v
    -2.27
    開設
    -2.25
    POSITIVE LOGITS
    </h3>
    4.34
    </sub>
    3.78
    逦
    3.48
     russa
    2.78
     robusto
    2.69
    ↵
    2.63
     kwamba
    2.50
    </strong>
    2.48
    瓩
    2.47
     edile
    2.44
    Activations Density 0.028%

    No Known Activations