© 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. 25761
    Prev
    Next
    INDEX
    Explanations

    Energy + specific domain

    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
     aggiungere
    -1.07
    mability
    -1.06
    includes
    -1.02
     améli
    -1.02
     STRE
    -0.98
    噢
    -0.96
     ピン
    -0.94
    such
    -0.94
    开始了
    -0.93
     rapidamente
    -0.92
    POSITIVE LOGITS
     efficient
    1.15
     drinks
    1.12
     dissipation
    1.09
     drink
    1.03
     consumption
    1.02
     levels
    1.02
     Robert
    1.02
     Verbraucher
    1.01
    通貨
    1.00
     conservation
    0.98
    Activations Density 0.023%

    No Known Activations