© 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. 10-GEMMASCOPE-RES-131K
    4. 90374
    Prev
    Next
    INDEX
    Explanations

    living organisms, people, or status

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

    terms referring to living organisms, particularly in biological and scientific 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_10/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
    1
    -1.71
    3
    -1.69
    4
    -1.39
    chures
    -1.35
    ctors
    -1.30
     nella
    -1.28
     nell
    -1.25
    7
    -1.23
     luego
    -1.23
     accompanying
    -1.20
    POSITIVE LOGITS
     five
    1.27
    live
    1.25
    dynamic
    1.23
     boste
    1.23
     live
    1.22
     it
    1.21
     this
    1.20
     first
    1.15
     higien
    1.14
     while
    1.13
    Activations Density 0.136%

    No Known Activations