© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66523
    Prev
    Next
    INDEX
    Explanations

    structured data attributes

    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
    :{
    
    -1.18
     such
    -1.18
     bereits
    -1.16
     into
    -1.13
    ↵↵
    -1.10
    тов
    -1.05
     restaur
    -1.01
    ({
    
    -1.01
     регистра
    -0.98
    向上
    -0.97
    POSITIVE LOGITS
     ocultar
    1.28
    raujo
    1.26
    えません
    1.22
     continúas
    1.18
    Penulis
    1.16
     almacenar
    1.16
     cerrar
    1.12
     awfully
    1.06
     aktiviteter
    1.05
    crivez
    1.02
    Activations Density 0.001%

    No Known Activations