© 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. 66555
    Prev
    Next
    INDEX
    Explanations

    how can

    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
    🩻
    -1.22
    念头
    -1.16
     textView
    -1.16
     emin
    -1.14
     можете
    -1.14
     précédent
    -1.13
     fonctionner
    -1.13
    ADVANTAGES
    -1.13
     histó
    -1.11
    好像
    -1.11
    POSITIVE LOGITS
     it
    2.09
     and
    1.75
     but
    1.41
     had
    1.30
     however
    1.26
     so
    1.21
     for
    1.20
    {
    1.15
    _
    1.13
    '
    1.13
    Activations Density 0.112%

    No Known Activations