© 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. 28913
    Prev
    Next
    INDEX
    Explanations

    sacrifice and compromise

    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
     August
    -1.38
     Clearly
    -1.38
     vết
    -1.37
    頻繁
    -1.35
    ichester
    -1.33
    ються
    -1.31
    .’”
    -1.30
    》：
    -1.30
     Always
    -1.30
    umid
    -1.28
    POSITIVE LOGITS
    趿
    1.73
     también
    1.70
     probablement
    1.66
    yaitu
    1.66
    也
    1.63
    feier
    1.61
     também
    1.59
     sein
    1.56
    einem
    1.51
     cũng
    1.50
    Activations Density 0.014%

    No Known Activations