© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106432
    Prev
    Next
    INDEX
    Explanations

    words starting with temp, tem, ter, tern

    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
    舊
    -0.78
    lidades
    -0.73
    Hurry
    -0.72
    jolly
    -0.72
     épais
    -0.69
    žev
    -0.69
     Зу
    -0.67
    Havolalar
    -0.66
    fører
    -0.66
    dank
    -0.66
    POSITIVE LOGITS
    perature
    0.96
     Temptation
    0.91
    temporal
    0.90
     tem
    0.85
     tempe
    0.81
     tes
    0.81
    plate
    0.81
     ter
    0.81
    Temporal
    0.80
     templ
    0.80
    Activations Density 0.052%

    No Known Activations