© 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. 73770
    Prev
    Next
    INDEX
    Explanations

    long periods of time

    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
     lepro
    -0.92
     THING
    -0.89
     چند
    -0.85
     weeks
    -0.82
     några
    -0.82
    녁
    -0.81
     cend
    -0.81
     WISCONSIN
    -0.80
     OBITUARY
    -0.79
     universitaria
    -0.79
    POSITIVE LOGITS
     long
    2.53
     a
    2.06
    long
    1.73
     longtemps
    1.61
     LONG
    1.61
     longest
    1.59
     долго
    1.53
    долго
    1.41
    Long
    1.38
     Long
    1.37
    Activations Density 0.031%

    No Known Activations