© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1990
    Prev
    Next
    INDEX
    Explanations

    compound medical and technical terms

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

    prefixes or compound terms often used in scientific and technical 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_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
     and
    -1.66
    明日は
    -1.30
     Ressources
    -1.30
    先週
    -1.28
     investissement
    -1.26
    もうすぐ
    -1.25
    𝑁
    -1.24
    まさかの
    -1.23
     existant
    -1.21
    ついに
    -1.20
    POSITIVE LOGITS
     그리고
    1.42
    ต่างๆ
    1.39
     will
    1.37
     sowie
    1.31
     can
    1.29
     незавер
    1.29
     serta
    1.27
     when
    1.27
     dibuat
    1.22
    Preparazione
    1.20
    Activations Density 0.295%

    No Known Activations