© 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. 10-GEMMASCOPE-RES-131K
    7. 42574
    Prev
    Next
    INDEX
    Explanations

    address / address-like identifiers

    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_10/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
    ógico
    -1.47
    "]();
    -1.35
    AMENT
    -1.35
    CHREIBUNG
    -1.31
    angsaan
    -1.31
    泐
    -1.27
    PLAUSE
    -1.26
     hadapan
    -1.26
    ];
    -1.25
     рублей
    -1.25
    POSITIVE LOGITS
     preocupado
    1.40
    缺点
    1.38
     nonostante
    1.36
     steder
    1.35
     comprehensively
    1.34
     evangé
    1.33
     a
    1.32
     eksemp
    1.31
     ,,
    1.27
     ‚
    1.26
    Activations Density 0.005%

    No Known Activations