© 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. 104665
    Prev
    Next
    INDEX
    Explanations

    generated by javadoc

    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
     different
    -1.30
    5
    -1.24
     even
    -1.20
     those
    -1.20
     only
    -1.20
     einem
    -1.19
     two
    -1.15
    7
    -1.14
     last
    -1.14
     other
    -1.10
    POSITIVE LOGITS
    となりました
    1.14
    garlic
    1.06
     feitas
    1.04
    ynchronously
    1.04
     bebés
    1.04
    たびに
    1.03
    gegangen
    1.03
    küche
    1.02
    zeugt
    1.02
     lác
    1.02
    Activations Density 0.001%

    No Known Activations