© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 70259
    Prev
    Next
    INDEX
    Explanations

    past or future 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
    otin
    -0.91
    gonic
    -0.88
    lateinit
    -0.86
    ils
    -0.85
    anten
    -0.84
    法官
    -0.84
    chten
    -0.82
     було
    -0.81
    valents
    -0.80
    飲料
    -0.79
    POSITIVE LOGITS
     year
    5.16
     months
    4.28
     years
    3.98
     month
    3.95
    year
    2.98
     año
    2.77
     Year
    2.61
    Months
    2.55
    month
    2.55
    Year
    2.55
    Activations Density 0.207%

    No Known Activations