© 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. 64995
    Prev
    Next
    INDEX
    Explanations

    executive, thank, or code snippets

    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
     Also
    -2.89
     While
    -2.86
    because
    -2.84
     takes
    -2.77
     provides
    -2.75
    Often
    -2.70
    Even
    -2.64
    There
    -2.64
    Usually
    -2.64
    Some
    -2.63
    POSITIVE LOGITS
     they
    2.53
    ᕮ
    2.48
    螃
    2.42
    ︐
    2.38
     geene
    2.36
     produk
    2.34
    ܆
    2.34
     perspek
    2.31
     gewi
    2.28
     heilige
    2.28
    Activations Density 0.009%

    No Known Activations