© 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. 34-GEMMASCOPE-RES-131K
    4. 2082
    Prev
    Next
    INDEX
    Explanations

    text preceding special characters

    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_34/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
    팀
    -0.92
    ؑ
    -0.81
     métallique
    -0.76
     casts
    -0.75
    处理器
    -0.75
    ейс
    -0.73
     Werkzeug
    -0.71
     möchten
    -0.71
    burton
    -0.70
    widual
    -0.69
    POSITIVE LOGITS
    küche
    0.86
    latex
    0.82
    ള്ള
    0.77
    Antwort
    0.77
    träglich
    0.75
    ヤー
    0.74
    🟢
    0.73
    möglichkeiten
    0.73
    Folge
    0.73
    
    0.72
    Activations Density 0.001%

    No Known Activations