© 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. 34-GEMMASCOPE-RES-131K
    7. 81647
    Prev
    Next
    INDEX
    Explanations

    settings configuration

    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
     پشتیبانی
    -0.93
     ESPECIAL
    -0.93
    identité
    -0.91
    Решение
    -0.91
    imbawa
    -0.88
    сылки
    -0.88
    之上
    -0.86
    踢
    -0.85
    穿上
    -0.85
     SOBRE
    -0.84
    POSITIVE LOGITS
     settings
    1.69
     setting
    1.69
     Settings
    1.54
     Setting
    1.53
    setting
    1.48
    settings
    1.37
    Settings
    1.32
    Setting
    1.27
     настройки
    1.26
     SETTING
    1.20
    Activations Density 0.015%

    No Known Activations