© 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. 64643
    Prev
    Next
    INDEX
    Explanations

    approximate time or duration

    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
     both
    -1.00
     frescas
    -0.84
     aastal
    -0.84
     sixteen
    -0.82
     eight
    -0.82
     τὴν
    -0.81
     six
    -0.81
    بدأ
    -0.81
    师
    -0.80
     निम्
    -0.80
    POSITIVE LOGITS
    approx
    1.41
    typically
    1.34
     примерно
    1.26
    ประมาณ
    1.20
     حدود
    1.16
    usually
    1.15
     typically
    1.14
     likely
    1.14
    approximately
    1.14
     généralement
    1.12
    Activations Density 0.089%

    No Known Activations