© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72936
    Prev
    Next
    INDEX
    Explanations

    days 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
     recientemente
    -1.16
     tým
    -1.13
     parecido
    -1.09
     recently
    -1.05
     then
    -0.98
     pomaga
    -0.97
     month
    -0.97
     hoeft
    -0.97
    たちに
    -0.97
     hebt
    -0.96
    POSITIVE LOGITS
     afternoon
    1.31
    urement
    1.23
     morning
    1.20
     evening
    1.11
     pagi
    1.06
    ußen
    1.05
    
    1.03
     day
    1.02
     versos
    1.01
     Ž
    1.00
    Activations Density 0.024%

    No Known Activations