© 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. 117299
    Prev
    Next
    INDEX
    Explanations

    number of years

    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
     weeks
    -1.36
     week
    -1.34
     semaine
    -1.33
     month
    -1.30
     meses
    -1.30
    Weeks
    -1.29
     Weeks
    -1.26
     mesi
    -1.23
     months
    -1.20
    month
    -1.20
    POSITIVE LOGITS
     years
    3.42
     year
    2.75
    year
    1.87
    years
    1.79
     Years
    1.59
     سال
    1.58
     года
    1.55
    YEAR
    1.55
    Years
    1.53
    Year
    1.50
    Activations Density 0.068%

    No Known Activations