© 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. 63691
    Prev
    Next
    INDEX
    Explanations

    time units and intervals

    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
     Biv
    -0.72
    Paula
    -0.71
     Fase
    -0.71
    kungen
    -0.70
     народов
    -0.69
     manila
    -0.69
     Andi
    -0.68
    intă
    -0.68
    iestety
    -0.68
     triples
    -0.68
    POSITIVE LOGITS
     period
    2.14
     unit
    1.73
    period
    1.68
     time
    1.66
     timeframe
    1.65
     TimeUnit
    1.63
    TimeUnit
    1.61
     periods
    1.57
     units
    1.55
     interval
    1.52
    Activations Density 0.040%

    No Known Activations