© 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. 9338
    Prev
    Next
    INDEX
    Explanations

    script outputs contents

    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
     before
    -1.51
     may
    -1.28
     other
    -1.27
     says
    -1.25
     women
    -1.21
     ennen
    -1.18
     or
    -1.15
     because
    -1.15
     testGet
    -1.14
     ενώ
    -1.14
    POSITIVE LOGITS
     Inſ
    1.34
     into
    1.27
     anadolu
    1.27
     ghz
    1.25
    וּ
    1.24
     paillettes
    1.22
     laver
    1.20
    𝒙
    1.19
     Профиль
    1.18
     uchiha
    1.17
    Activations Density 0.374%

    No Known Activations