© 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. 22-GEMMASCOPE-RES-131K
    7. 67093
    Prev
    Next
    INDEX
    Explanations

    energy, alertness, and fatigue

    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_22/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
     to
    -1.47
    几年
    -0.99
     الحكومة
    -0.99
     geboten
    -0.98
     paziente
    -0.98
     tecniche
    -0.97
    ashqai
    -0.96
     pijn
    -0.96
    Continua
    -0.96
     大き
    -0.94
    POSITIVE LOGITS
     afternoon
    1.38
     office
    1.34
    bảng
    1.31
     productivity
    1.28
     boost
    1.27
     day
    1.24
     актри
    1.24
     morning
    1.23
     Decke
    1.23
     caffeine
    1.20
    Activations Density 0.044%

    No Known Activations