© 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. 12383
    Prev
    Next
    INDEX
    Explanations

    slogans and taglines

    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
     glaubt
    -2.53
     you
    -2.38
     It
    -2.27
    糅
    -2.27
     algún
    -2.23
    我对
    -2.19
    rowable
    -2.17
    捭
    -2.16
     them
    -2.16
    東南
    -2.14
    POSITIVE LOGITS
    '
    3.11
    er
    3.03
    up
    2.55
     slogans
    2.38
    ti
    2.34
    ss
    2.17
    re
    2.16
    们的
    2.14
     frontiers
    2.14
    0
    2.00
    Activations Density 0.001%

    No Known Activations