© 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. 10-GEMMASCOPE-RES-131K
    7. 104488
    Prev
    Next
    INDEX
    Explanations

    coiled-coil, contract cancer, discharged assumption

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

    words or phrases related to formal or technical terminology, particularly endings of words like "coil", "ize", "nic".

    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
    '
    -2.50
     people
    -1.60
    ‘
    -1.58
    Then
    -1.55
     then
    -1.51
     welches
    -1.42
    He
    -1.38
     isang
    -1.34
    Moreover
    -1.30
     Effekt
    -1.27
    POSITIVE LOGITS
     ſou
    1.74
     良品
    1.61
    kelijkheid
    1.59
    Ehh
    1.57
    »?
    1.55
    ::::::::::::::::
    1.55
    JAMIN
    1.54
    Mmmm
    1.52
     člán
    1.51
    éb
    1.49
    Activations Density 0.050%

    No Known Activations