© 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. 13061
    Prev
    Next
    INDEX
    Explanations

    descriptions and technical terms

    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
    armani
    -1.17
     orsz
    -1.16
    madonna
    -1.16
    casse
    -1.09
    tenis
    -1.09
     també
    -1.05
    ELIA
    -1.04
     Aún
    -1.03
     главных
    -1.02
    celine
    -1.01
    POSITIVE LOGITS
    Transk
    1.41
    معرفی
    1.37
    Tils
    1.30
    توضیحات
    1.30
    Ilustra
    1.30
    ಔ
    1.27
    Aantal
    1.24
    俨
    1.24
    Recept
    1.24
    Descriere
    1.23
    Activations Density 0.003%

    No Known Activations