© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78701
    Prev
    Next
    INDEX
    Explanations

    economic cycles

    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
    Lietu
    -0.78
     bölüm
    -0.75
     Sudbury
    -0.75
     melden
    -0.73
     sprá
    -0.72
    jene
    -0.72
     nettoyage
    -0.72
    STATIC
    -0.71
     сала
    -0.71
     surtido
    -0.68
    POSITIVE LOGITS
     cycle
    1.66
     cyclical
    1.52
     cycles
    1.52
     Cycle
    1.49
    cycle
    1.48
    cyc
    1.32
     cyclic
    1.30
    cycles
    1.30
     Cycles
    1.27
     Cyc
    1.27
    Activations Density 0.018%

    No Known Activations