© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62557
    Prev
    Next
    INDEX
    Explanations

    energy efficient

    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
    Negative Logits
    čaj
    -0.83
    aroon
    -0.82
    っていると
    -0.81
     finales
    -0.80
    oue
    -0.79
    триму
    -0.79
    芪
    -0.79
    SECUR
    -0.79
    疤
    -0.77
    olidation
    -0.75
    POSITIVE LOGITS
     energy
    2.50
    Energy
    1.85
     Energy
    1.84
    energy
    1.82
     Energie
    1.57
     thermal
    1.49
     ENERGY
    1.41
    ENERGY
    1.41
     energía
    1.41
     energie
    1.34
    Activations Density 0.029%

    No Known Activations