© 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. 73410
    Prev
    Next
    INDEX
    Explanations

    energy and certificates

    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
    她和
    -0.77
     dissa
    -0.77
    vedať
    -0.74
     ACK
    -0.71
    roff
    -0.70
     subtra
    -0.69
     appea
    -0.68
     faucet
    -0.68
     الجز
    -0.68
     확
    -0.68
    POSITIVE LOGITS
     energy
    1.36
    Energy
    1.22
    energy
    1.20
     Energy
    1.19
     certificate
    1.16
     certificates
    1.04
     rating
    1.02
     энерго
    0.95
    Certificate
    0.95
     Certificate
    0.91
    Activations Density 0.005%

    No Known Activations