© 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. 70004
    Prev
    Next
    INDEX
    Explanations

    recurring temporal events

    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
    erunner
    -1.14
     eeuw
    -1.11
     kellett
    -1.09
    arching
    -1.09
    lapping
    -1.09
    joined
    -1.09
    ’:
    -1.08
    ̨
    -1.08
    decided
    -1.07
    joyed
    -1.06
    POSITIVE LOGITS
     year
    2.80
     time
    2.42
     month
    2.16
     day
    2.05
     week
    1.97
     years
    1.72
     weeks
    1.70
     months
    1.69
     has
    1.65
     morning
    1.59
    Activations Density 0.028%

    No Known Activations