© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77174
    Prev
    Next
    INDEX
    Explanations

    get or retrieve data

    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
    َع
    -0.91
    ඝ
    -0.90
    stappen
    -0.90
    MediaStore
    -0.89
     conçus
    -0.88
    RIQUE
    -0.85
    isissez
    -0.85
    为什么要
    -0.84
    ให้
    -0.84
    岐阜
    -0.83
    POSITIVE LOGITS
     from
    1.91
     information
    1.84
     rid
    1.51
     current
    1.39
     info
    1.37
     list
    1.34
     details
    1.30
     names
    1.20
     number
    1.15
     value
    1.13
    Activations Density 0.155%

    No Known Activations