© 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. 34-GEMMASCOPE-RES-131K
    7. 118852
    Prev
    Next
    INDEX
    Explanations

    spent time with

    np_acts-logits-general · gemini-2.5-flash-lite

    the mentions of spans of time or durations (e.g. days, weeks, years, time)

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     that
    -1.82
     continued
    -1.34
     many
    -1.27
     always
    -1.25
     sánchez
    -1.20
     started
    -1.17
     utilizz
    -1.17
    álise
    -1.17
     melalui
    -1.16
     spend
    -1.16
    POSITIVE LOGITS
     in
    2.17
     on
    1.55
    视着
    1.30
     blessure
    1.19
    Either
    1.10
    wiaty
    1.05
     at
    1.04
     outdoors
    1.04
     között
    1.02
     εκεί
    1.02
    Activations Density 0.020%

    No Known Activations