© 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. 22-GEMMASCOPE-RES-131K
    7. 25756
    Prev
    Next
    INDEX
    Explanations

    duration and time references

    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_22/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
    最初は
    -0.98
     administrativo
    -0.84
    最近は
    -0.82
     Shetterly
    -0.82
    現在の
    -0.81
    ittä
    -0.81
     اولیه
    -0.78
    Eerste
    -0.78
    лять
    -0.77
    一度
    -0.75
    POSITIVE LOGITS
     long
    1.61
     years
    1.45
     longer
    1.43
     lifetime
    1.38
     future
    1.37
     permanent
    1.27
     year
    1.27
     past
    1.24
     previous
    1.22
     lifelong
    1.20
    Activations Density 0.099%

    No Known Activations