© 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. 75067
    Prev
    Next
    INDEX
    Explanations

    markup attributes and values

    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_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
     speziellen
    -1.59
    裡
    -1.52
     lesquels
    -1.44
     besonderen
    -1.38
    ೣ
    -1.38
     maravilh
    -1.35
     erheb
    -1.30
     spezi
    -1.30
     gän
    -1.29
    光の
    -1.27
    POSITIVE LOGITS
    噚
    1.77
     and
    1.60
     untuk
    1.59
     including
    1.57
    while
    1.53
     متحده
    1.51
    ukunfts
    1.50
     蛇
    1.47
     again
    1.47
     of
    1.47
    Activations Density 0.000%

    No Known Activations