© 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. 68349
    Prev
    Next
    INDEX
    Explanations

    document, }, $(, int

    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
     protéger
    -1.48
     rése
    -1.47
    theres
    -1.41
     pelu
    -1.40
    dengan
    -1.39
    reached
    -1.38
     plafon
    -1.37
     murales
    -1.34
     péché
    -1.34
     américa
    -1.34
    POSITIVE LOGITS
     it
    1.69
     some
    1.55
     by
    1.55
     two
    1.46
     even
    1.41
     they
    1.38
     taking
    1.34
     then
    1.29
     because
    1.27
     took
    1.24
    Activations Density 0.005%

    No Known Activations