© 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. 11139
    Prev
    Next
    INDEX
    Explanations

    role, third, great

    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
     计划
    -0.94
    Ivo
    -0.93
    ]}>
    -0.88
     nachdem
    -0.84
    FOTO
    -0.83
     zwei
    -0.83
    되었다
    -0.80
    ～～～～
    -0.79
     排行
    -0.79
    ➢
    -0.79
    POSITIVE LOGITS
     this
    0.99
     друго
    0.98
    Nazionale
    0.92
     our
    0.91
    になれば
    0.90
     naszego
    0.89
     essas
    0.89
     vastu
    0.89
    millan
    0.88
    땃
    0.88
    Activations Density 0.062%

    No Known Activations