© 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. 99700
    Prev
    Next
    INDEX
    Explanations

    compound nouns and descriptive phrases

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

    The neuron is triggered by major topical or domain‐specific keywords and proper‐noun phrases—e.g. the names of papers, books, technical terms, or article titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    
    -1.48
     一
    -1.47
     things
    -1.44
     Perſ
    -1.41
     unbelievably
    -1.38
     manguera
    -1.34
     estranho
    -1.34
     znajdu
    -1.32
     ſtre
    -1.30
     bén
    -1.30
    POSITIVE LOGITS
     and
    1.92
     on
    1.46
     at
    1.43
     in
    1.39
     with
    1.28
    相关文章
    1.25
    _{-}
    1.24
      (
    1.22
    ”,
    1.21
    诸多
    1.21
    Activations Density 0.596%

    No Known Activations