© 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. 36290
    Prev
    Next
    INDEX
    Explanations

    new and latest products

    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
     it
    -1.55
     if
    -1.48
    It
    -1.23
     christlichen
    -1.16
     there
    -1.13
     occasionally
    -1.13
     semillas
    -1.11
    離婚
    -1.11
    dž
    -1.10
    skapet
    -1.09
    POSITIVE LOGITS
    Customers
    1.38
     fiabilidad
    1.34
     '.';
    1.34
     heilig
    1.32
     gefe
    1.26
     nimmer
    1.25
     deſt
    1.23
     produkt
    1.23
     Rijks
    1.23
    ер
    1.22
    Activations Density 0.064%

    No Known Activations