© 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. 7139
    Prev
    Next
    INDEX
    Explanations

    top ranks and ratings

    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
     slav
    -0.97
    jdzie
    -0.97
     gethan
    -0.94
     dergleichen
    -0.93
     folgte
    -0.93
    🇲
    -0.92
     hué
    -0.91
    ご購入
    -0.91
    äher
    -0.89
    ARES
    -0.89
    POSITIVE LOGITS
     in
    1.41
     list
    1.40
     ranking
    1.38
     of
    1.36
     rankings
    1.18
     earners
    1.16
     countdown
    1.05
     most
    1.02
     ranked
    0.97
     reasons
    0.93
    Activations Density 0.030%

    No Known Activations