© 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. 22-GEMMASCOPE-RES-131K
    7. 70829
    Prev
    Next
    INDEX
    Explanations

    macrophages and glia

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

    immune cells, particularly macrophages, microglia, and other related immune system components.

    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_22/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
     Longitud
    -1.31
    wał
    -1.30
     Einfluß
    -1.30
    物的
    -1.26
     студент
    -1.23
     محبوب
    -1.23
    нули
    -1.21
     Gipfel
    -1.21
     evaporation
    -1.19
    iecie
    -1.19
    POSITIVE LOGITS
    alamu
    1.30
    Zeneca
    1.21
     terça
    1.12
     contribuir
    1.06
     gradualmente
    1.05
     estético
    1.05
    簠
    1.04
     puramente
    1.04
     responding
    1.03
     LoginComponent
    1.03
    Activations Density 0.143%

    No Known Activations