© 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. 28050
    Prev
    Next
    INDEX
    Explanations

    Supreme Court, concentration camp, checkpoint inhibitor

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

    legal and scientific terminology related to regulations, court decisions, and medical/biological classifications.

    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
     como
    -1.09
    sopa
    -1.09
     kanskje
    -1.09
     antigo
    -1.07
     Seelen
    -1.06
     doit
    -1.05
     directamente
    -1.05
     guerr
    -1.05
    ḿ
    -1.04
    perhaps
    -1.03
    POSITIVE LOGITS
     particulières
    1.13
    ASTIC
    1.06
     personnelles
    1.05
     essentielles
    1.05
    IMUM
    1.04
     explication
    1.03
     accueillir
    1.02
     spéciales
    1.00
     psychotic
    0.99
    門口
    0.98
    Activations Density 0.186%

    No Known Activations