© 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. 84021
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    ॠ
    -0.94
     Bruder
    -0.87
     eenvou
    -0.84
     esfuerzo
    -0.83
     especiales
    -0.83
    seguida
    -0.82
    quarie
    -0.81
    Примечание
    -0.80
     felizes
    -0.80
    Aman
    -0.80
    POSITIVE LOGITS
     beispielsweise
    1.18
     Например
    1.17
     например
    1.17
     bijvoorbeeld
    1.11
    例えば
    1.10
    例如
    1.09
     například
    1.07
    Например
    1.04
    たとえば
    1.03
     például
    1.00
    Activations Density 0.114%

    No Known Activations