© 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. 67613
    Prev
    Next
    INDEX
    Explanations

    dates or periods

    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
    rån
    -1.04
    Ингредиенты
    -1.03
    ië
    -1.00
    鯓
    -0.98
    ॐ
    -0.98
    ICIOS
    -0.98
    
    -0.96
     porno
    -0.95
    ハーブ
    -0.95
    ricos
    -0.95
    POSITIVE LOGITS
     supposedly
    1.25
     services
    1.19
     service
    1.19
     this
    1.13
     pourtant
    1.13
     servicios
    1.12
     their
    1.10
    所谓的
    1.07
     пыта
    1.06
     suplementos
    1.05
    Activations Density 0.015%

    No Known Activations