© 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. 2738
    Prev
    Next
    INDEX
    Explanations

    midterm elections and time periods

    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
     presidential
    -1.00
     Presidential
    -0.90
     FishBase
    -0.80
    Presidential
    -0.74
    oyu
    -0.68
    футбо
    -0.67
     SATURDAY
    -0.66
    hado
    -0.65
    ตรี
    -0.64
    पूर्ण
    -0.64
    POSITIVE LOGITS
     midterm
    3.97
     mid
    3.70
    Mid
    3.31
     Mid
    3.11
    mid
    3.05
    MID
    2.34
     MID
    2.19
     mids
    1.98
     midpoint
    1.91
     mida
    1.74
    Activations Density 0.033%

    No Known Activations