© 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. 93387
    Prev
    Next
    INDEX
    Explanations

    Michael Dwyer or adapter code

    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
     to
    -1.13
     Interior
    -0.84
     Descripción
    -0.82
    пыт
    -0.82
     HomeComponent
    -0.81
     Crédito
    -0.81
     Dishwasher
    -0.81
     исче
    -0.81
     Wrocław
    -0.79
     وغ
    -0.79
    POSITIVE LOGITS
     limitado
    1.17
     it
    1.15
     memutus
    1.07
    Schweiz
    1.07
    Materiaal
    1.06
     finalizar
    1.02
    頑張って
    1.01
    Kleur
    0.98
     entidades
    0.97
     températures
    0.94
    Activations Density 0.001%

    No Known Activations