© 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. 11809
    Prev
    Next
    INDEX
    Explanations

    code structure syntax

    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
     its
    -1.23
     erila
    -1.02
     vooral
    -1.01
     (!__
    -0.99
     ennen
    -0.97
     unless
    -0.95
     \
    -0.94
    [\
    -0.93
    ફ
    -0.93
     следующие
    -0.92
    POSITIVE LOGITS
    競技
    1.01
     (
    1.00
    alahkan
    0.98
    ף
    0.95
    Sentiment
    0.94
    责任编辑
    0.94
    cinq
    0.93
     doméstica
    0.93
    するという
    0.92
    りで
    0.92
    Activations Density 0.010%

    No Known Activations