© 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. 22-GEMMASCOPE-RES-131K
    4. 70551
    Prev
    Next
    INDEX
    Explanations

    units followed by numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     who
    -1.19
    我国
    -1.15
     подозре
    -0.98
     strategy
    -0.98
    …
    -0.96
    toDouble
    -0.93
    >"+
    -0.92
    ₫
    -0.91
    resultSet
    -0.90
    们
    -0.90
    POSITIVE LOGITS
    中には
    1.19
    それも
    1.19
    <bos>
    1.15
    個人的には
    1.13
    <0xA3>
    1.12
     Ketika
    1.11
     ravages
    1.11
     Beberapa
    1.10
     Lakukan
    1.07
    そういった
    1.06
    Activations Density 0.005%

    No Known Activations