© 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. 47838
    Prev
    Next
    INDEX
    Explanations

    inflammatory cell infiltration

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

    This neuron detects descriptions of inflammatory cellular infiltration in tissues.

    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_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
     bloggers
    -0.82
     Nagel
    -0.78
    筲
    -0.74
     whips
    -0.74
    interior
    -0.72
    madamente
    -0.71
     wą
    -0.70
    Loops
    -0.69
     solubility
    -0.68
     aerolí
    -0.68
    POSITIVE LOGITS
     infiltration
    2.61
     infiltr
    2.30
     infiltrate
    2.23
     infiltrated
    1.95
     infil
    1.91
     influx
    1.32
     lymphocytes
    1.31
    filtr
    1.22
    filtration
    1.20
     leuk
    1.16
    Activations Density 0.203%

    No Known Activations