© 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. 55664
    Prev
    Next
    INDEX
    Explanations

    research project grant cancer foundation pope francis

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

    research funding and grant acknowledgement sections in academic papers.

    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
    héro
    -1.02
    sommer
    -0.97
     viviendas
    -0.95
     Fungsi
    -0.92
     nemico
    -0.91
     regista
    -0.88
    plakat
    -0.87
    就不会
    -0.85
    Termine
    -0.83
     parche
    -0.83
    POSITIVE LOGITS
     Young
    0.98
     "
    0.96
     pály
    0.96
     young
    0.95
     scheme
    0.95
     seed
    0.90
     “
    0.87
     grant
    0.85
     specific
    0.85
    Young
    0.84
    Activations Density 0.020%

    No Known Activations