© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99143
    Prev
    Next
    INDEX
    Explanations

    energy and standby efficiency

    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
     summarize
    -0.71
    哌
    -0.70
     sabores
    -0.69
     locate
    -0.69
     safe
    -0.69
     taste
    -0.68
     Olom
    -0.68
    butt
    -0.67
     tasty
    -0.66
     безопас
    -0.66
    POSITIVE LOGITS
     energy
    1.31
     standby
    1.18
    Energy
    1.16
     ENERGY
    1.16
     Energy
    1.14
    Eco
    1.09
     efficiency
    1.08
     Standby
    1.08
    energy
    1.08
     Eco
    1.06
    Activations Density 0.014%

    No Known Activations