© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27307
    Prev
    Next
    INDEX
    Explanations

    days of the week and time

    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
     and
    -1.45
     this
    -1.41
     потім
    -1.31
     дуже
    -1.25
     then
    -1.23
     or
    -1.23
     bepa
    -1.15
    libatkan
    -1.15
     теперь
    -1.14
     тогда
    -1.13
    POSITIVE LOGITS
     morning
    1.62
    b
    1.41
     afternoon
    1.36
     also
    1.25
     Today
    1.21
    p
    1.19
    并未
    1.16
    w
    1.13
    ir
    1.13
    le
    1.11
    Activations Density 0.021%

    No Known Activations