© 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. 34-GEMMASCOPE-RES-131K
    7. 30772
    Prev
    Next
    INDEX
    Explanations

    day-to-day

    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
     day
    -1.93
    day
    -1.55
    Day
    -1.42
     DAY
    -1.41
     Day
    -1.35
     день
    -1.25
     día
    -1.23
    DAY
    -1.09
     дня
    -0.98
     ziua
    -0.97
    POSITIVE LOGITS
     to
    2.41
    to
    1.16
     To
    0.96
    To
    0.92
     به
    0.88
    everyday
    0.86
     codzien
    0.83
    normal
    0.82
     TO
    0.80
     everyday
    0.80
    Activations Density 0.009%

    No Known Activations