© 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. 15449
    Prev
    Next
    INDEX
    Explanations

    days of the week and times

    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
    iamo
    -1.05
    今日も
    -1.04
     記念
    -1.03
     repeatedly
    -1.03
     avevano
    -1.02
     resultaten
    -1.02
     fiecare
    -1.01
     ottenere
    -0.98
     ajutor
    -0.97
    每一
    -0.95
    POSITIVE LOGITS
     Saturday
    1.05
     Sunday
    1.01
     doméstica
    0.98
    なければならない
    0.98
    Étymologie
    0.98
     we
    0.98
    好評
    0.97
    ditionally
    0.96
    ≍
    0.95
     PUEDE
    0.95
    Activations Density 0.011%

    No Known Activations