© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109457
    Prev
    Next
    INDEX
    Explanations

    energy and vitality

    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
    vent
    -0.82
    ICAS
    -0.80
    院校
    -0.78
    бір
    -0.78
     pleasures
    -0.77
    ḿ
    -0.76
    ASG
    -0.76
    °/
    -0.75
    vention
    -0.75
     akka
    -0.75
    POSITIVE LOGITS
     energy
    4.03
    energy
    2.95
     energies
    2.92
     Energy
    2.72
    Energy
    2.56
     energía
    2.33
    能量
    2.27
     ENERGY
    2.25
     vibes
    2.19
    ENERGY
    2.19
    Activations Density 0.026%

    No Known Activations