© 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. 93005
    Prev
    Next
    INDEX
    Explanations

    amino acids, Duration, PG production, slide

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

    scientific and technical terminology, especially in biochemistry, mathematics, and programming contexts.

    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
    ADING
    -1.09
     duradero
    -1.07
     sekä
    -1.05
    eced
    -1.04
     animada
    -1.02
     notamment
    -1.02
    went
    -1.02
    FONTE
    -1.02
    ticos
    -0.99
    ENDENT
    -0.99
    POSITIVE LOGITS
     in
    1.39
     on
    1.34
     when
    1.13
    0
    1.09
     like
    1.05
     by
    1.03
     hvit
    1.03
     which
    1.03
    ienė
    1.03
     so
    1.01
    Activations Density 0.095%

    No Known Activations