© 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. 92794
    Prev
    Next
    INDEX
    Explanations

    Easter dates and holidays

    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
     compleanno
    -1.00
     valentine
    -0.88
    iritual
    -0.85
     Entscheidungen
    -0.82
     noël
    -0.82
     navidad
    -0.79
    𐌴
    -0.78
     valentines
    -0.76
    ⑼
    -0.76
    ulage
    -0.76
    POSITIVE LOGITS
     Gründ
    0.98
     Good
    0.93
     Mau
    0.88
     Apr
    0.86
     Easter
    0.81
     April
    0.80
    APRIL
    0.76
     Palm
    0.76
     /(
    0.76
     pasión
    0.73
    Activations Density 0.015%

    No Known Activations