© 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. 79543
    Prev
    Next
    INDEX
    Explanations

    multi-word phrases and compounds

    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
     kré
    -1.52
     tunik
    -1.46
     vêtements
    -1.46
     tênis
    -1.45
     bluza
    -1.44
     huiles
    -1.44
    และ
    -1.43
    𝗞
    -1.38
     DURING
    -1.38
    鶿
    -1.36
    POSITIVE LOGITS
    is
    1.57
     will
    1.49
     not
    1.48
    J
    1.47
    h
    1.45
    G
    1.45
    T
    1.44
    no
    1.43
     no
    1.42
    at
    1.41
    Activations Density 0.078%

    No Known Activations