© 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. 60300
    Prev
    Next
    INDEX
    Explanations

    Copyright notice

    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
     ją
    -1.05
    🍍
    -0.83
    construction
    -0.81
     密码
    -0.80
     város
    -0.80
     её
    -0.79
    nitř
    -0.79
     آن
    -0.78
    ênero
    -0.78
     извест
    -0.77
    POSITIVE LOGITS
    Copyright
    1.17
     email
    1.03
     Copyright
    1.01
    鎢
    0.84
     modified
    0.82
     enfermos
    0.82
     izman
    0.82
     Dennoch
    0.81
    Ecole
    0.81
    ikk
    0.80
    Activations Density 0.023%

    No Known Activations