© 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. 82721
    Prev
    Next
    INDEX
    Explanations

    news organizations

    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
     inoxidable
    -0.84
    }}
    -0.80
    Instagram
    -0.75
     Pyongyang
    -0.75
    Disciplina
    -0.74
    DYNAMIC
    -0.73
     Zelensky
    -0.73
    Attack
    -0.73
     Ukrainian
    -0.73
     során
    -0.72
    POSITIVE LOGITS
    Thomson
    1.02
     VICE
    1.00
     Thomson
    0.94
     DW
    0.90
     Global
    0.88
     Quartz
    0.84
     トレー
    0.82
     víc
    0.81
    Correspond
    0.81
     Jazeera
    0.81
    Activations Density 0.036%

    No Known Activations