© 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. 22-GEMMASCOPE-RES-131K
    7. 25252
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
     each
    -1.02
     resulting
    -1.00
     which
    -0.98
     last
    -0.97
     estrena
    -0.96
    íra
    -0.95
     cómoda
    -0.93
     souhaite
    -0.92
    })_{
    -0.91
     começa
    -0.90
    POSITIVE LOGITS
     will
    1.21
     of
    1.05
    aperto
    0.97
    árol
    0.94
     nostri
    0.92
    مشخص
    0.90
    نتیجه
    0.88
    ps
    0.87
     expédi
    0.86
     виправи
    0.86
    Activations Density 0.003%

    No Known Activations