© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102963
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
    賀状
    -0.91
     Kecil
    -0.85
    Maybe
    -0.84
    unl
    -0.81
     maybe
    -0.81
    Compose
    -0.80
    Kegiatan
    -0.79
     Maybe
    -0.78
     conseille
    -0.77
     周年
    -0.77
    POSITIVE LOGITS
     hours
    1.16
     overnight
    1.05
     hrs
    1.01
    hours
    0.96
     durations
    0.95
     hab
    0.92
     periods
    0.91
    Hours
    0.89
     hr
    0.86
     hour
    0.85
    Activations Density 0.099%

    No Known Activations