© 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. 28542
    Prev
    Next
    INDEX
    Explanations

    if and only if

    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
    küche
    -0.95
     tracción
    -0.93
    ENDIX
    -0.90
    倢
    -0.90
     korrekt
    -0.89
     icônes
    -0.88
     dios
    -0.87
     manhã
    -0.86
    ﻷ
    -0.85
    "}>
    -0.85
    POSITIVE LOGITS
    匾
    1.07
     to
    0.92
     D
    0.90
     g
    0.90
     S
    0.90
    τες
    0.87
     honest
    0.87
     k
    0.86
     into
    0.85
    luck
    0.84
    Activations Density 0.000%

    No Known Activations