© 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. 76062
    Prev
    Next
    INDEX
    Explanations

    daily or every day

    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
    setTimeout
    -1.12
    cila
    -1.02
     Jahres
    -1.00
    isNullOrEmpty
    -0.98
     Annual
    -0.96
    alignSelf
    -0.92
    postcss
    -0.86
    οντας
    -0.84
     Hül
    -0.82
     postIndex
    -0.81
    POSITIVE LOGITS
     daily
    6.22
     every
    5.50
     everyday
    5.22
    每天
    4.78
    daily
    4.53
    毎日
    4.25
     each
    4.22
     каждый
    4.19
    every
    4.03
    everyday
    4.03
    Activations Density 0.313%

    No Known Activations