© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 846
    Prev
    Next
    INDEX
    Explanations

    long before, until, or ago

    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
     prior
    -2.06
    prior
    -1.77
    Prior
    -1.59
     Prior
    -1.52
     PRIOR
    -1.45
    PRIOR
    -1.37
     vooraf
    -1.07
    pre
    -1.06
     заранее
    -1.01
     preceding
    -0.96
    POSITIVE LOGITS
     until
    1.95
     till
    1.93
     before
    1.43
    Until
    1.41
     to
    1.38
     Until
    1.34
     til
    1.33
    Till
    1.28
    till
    1.20
     sampai
    1.20
    Activations Density 0.023%

    No Known Activations