© 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. 819
    Prev
    Next
    INDEX
    Explanations

    div and li tag content

    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
    or
    -2.36
    ↵
    -2.14
    at
    -2.09
    ll
    -1.89
     ―
    -1.87
     nordrhein
    -1.83
     example
    -1.80
    3
    -1.78
     Gästen
    -1.76
     he
    -1.74
    POSITIVE LOGITS
     durs
    2.00
    ’).
    1.99
    櫺
    1.91
     lez
    1.89
    砗
    1.89
     sors
    1.82
     femelle
    1.80
     engend
    1.80
     profonde
    1.77
    bkz
    1.77
    Activations Density 0.017%

    No Known Activations