© 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. 101610
    Prev
    Next
    INDEX
    Explanations

    explaining relationships using which

    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
     if
    -1.20
    𝘇
    -1.18
     nestled
    -1.16
     zůst
    -1.14
     before
    -1.11
     still
    -1.11
     may
    -1.09
     when
    -1.09
    .”.
    -1.09
     this
    -1.08
    POSITIVE LOGITS
     to
    1.61
     récemment
    1.58
     recientes
    1.57
    %',
    1.48
    轵
    1.41
     manejar
    1.40
    %),
    1.37
    蔟
    1.36
    “[
    1.36
     recently
    1.36
    Activations Density 0.103%

    No Known Activations