© 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. 70025
    Prev
    Next
    INDEX
    Explanations

    built or centered around

    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
    Bedankt
    -0.88
     Boucher
    -0.84
    当时
    -0.80
    nische
    -0.80
    Maak
    -0.79
    缅
    -0.79
    Inhalts
    -0.79
    ױ
    -0.78
    쁨
    -0.78
    ⓣ
    -0.77
    POSITIVE LOGITS
     around
    6.25
    around
    4.19
    Around
    4.03
     вокруг
    3.75
     Around
    3.75
     autour
    3.66
     alrededor
    3.47
     AROUND
    3.33
    AROUND
    3.00
     حول
    2.95
    Activations Density 0.070%

    No Known Activations