© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84381
    Prev
    Next
    INDEX
    Explanations

    political outcomes and consequences

    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
    ׇ
    -1.55
     anúncios
    -1.42
     perpétu
    -1.36
     recomendación
    -1.35
     fald
    -1.31
     soportes
    -1.30
     lámparas
    -1.26
    sometimes
    -1.26
    boucles
    -1.24
     drinken
    -1.23
    POSITIVE LOGITS
     three
    1.56
     two
    1.52
     will
    1.46
     an
    1.41
     pre
    1.41
    ִּ
    1.34
     anti
    1.34
     in
    1.31
     people
    1.31
     strategy
    1.30
    Activations Density 0.073%

    No Known Activations