© 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. 36110
    Prev
    Next
    INDEX
    Explanations

    distributions collections

    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
     heating
    -0.89
    emotional
    -0.85
     trio
    -0.85
     ports
    -0.83
    Barrel
    -0.82
     three
    -0.82
    Elemental
    -0.81
    Supers
    -0.81
     two
    -0.80
     main
    -0.80
    POSITIVE LOGITS
     recrutement
    0.99
    nyv
    0.92
     populous
    0.89
     population
    0.88
     Yojana
    0.88
     espoir
    0.87
     populations
    0.83
    тні
    0.82
     chinos
    0.82
    melden
    0.82
    Activations Density 0.144%

    No Known Activations