© 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. 105729
    Prev
    Next
    INDEX
    Explanations

    specific names and titles

    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
     damaligen
    -1.63
    Again
    -1.41
    These
    -1.33
     damals
    -1.33
     célé
    -1.30
    upuncture
    -1.29
     Hinsicht
    -1.28
     wiederum
    -1.27
    После
    -1.26
    Increasing
    -1.23
    POSITIVE LOGITS
     this
    1.65
     it
    1.49
    レクション
    1.39
     their
    1.39
     how
    1.38
     on
    1.27
     the
    1.27
    才行
    1.26
     not
    1.23
     XXXIII
    1.23
    Activations Density 0.002%

    No Known Activations