© 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. 75314
    Prev
    Next
    INDEX
    Explanations

    simply the flip there you

    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
    KJV
    -1.11
     wichtigste
    -1.08
     gudang
    -1.05
     kuliah
    -1.05
     different
    -1.05
     Mijn
    -1.04
     العديد
    -1.02
     различни
    -1.02
    euros
    -1.02
    usd
    -1.02
    POSITIVE LOGITS
     don
    1.45
     keep
    1.27
    :^{
    1.23
    прочем
    1.23
     bonus
    1.20
     you
    1.20
     isn
    1.17
    你
    1.16
     víc
    1.16
     //
    1.13
    Activations Density 0.027%

    No Known Activations