© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15457
    Prev
    Next
    INDEX
    Explanations

    dates and months after "on"

    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_10/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
    dicos
    -1.64
     vicenda
    -1.56
    rscheinlichkeit
    -1.56
    ൻ
    -1.55
    ὴν
    -1.52
    ㎞
    -1.49
    gemar
    -1.48
    ⃙
    -1.48
     if
    -1.47
    zeigt
    -1.47
    POSITIVE LOGITS
     December
    1.95
    \
    1.90
    </i>
    1.76
     October
    1.76
     
    1.71
     January
    1.70
     Wednesday
    1.66
     July
    1.66
     Tuesday
    1.60
     June
    1.59
    Activations Density 0.075%

    No Known Activations