© 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. 22-GEMMASCOPE-RES-131K
    7. 39687
    Prev
    Next
    INDEX
    Explanations

    time periods

    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_22/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
     of
    -1.79
     what
    -1.70
     how
    -1.55
     on
    -1.51
    〜！
    -1.38
     inapropiados
    -1.35
     at
    -1.34
     EVERY
    -1.33
    〜。
    -1.33
     originali
    -1.32
    POSITIVE LOGITS
     last
    1.77
     ensuing
    1.50
     days
    1.48
     years
    1.45
     latter
    1.43
    igth
    1.35
     week
    1.32
    푉
    1.32
     parceria
    1.32
    Potencia
    1.31
    Activations Density 0.060%

    No Known Activations