© 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. 28267
    Prev
    Next
    INDEX
    Explanations

    I followed by am, was, were, had

    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
     your
    -1.67
     you
    -1.59
    cnbc
    -1.40
    を目指す
    -1.38
     zdan
    -1.36
     będ
    -1.32
     ulub
    -1.30
     wzglę
    -1.29
     cechy
    -1.27
     then
    -1.27
    POSITIVE LOGITS
     Instal
    1.20
    でしょうね
    1.20
     possibly
    1.20
    as
    1.16
    确实
    1.10
     lauk
    1.09
    以上です
    1.09
    av
    1.09
    Siapa
    1.08
    臨床
    1.08
    Activations Density 0.027%

    No Known Activations