© 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. 79151
    Prev
    Next
    INDEX
    Explanations

    April and Easter

    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
    November
    -2.55
    October
    -2.52
     November
    -2.38
    Christmas
    -2.36
     October
    -2.36
     Christmas
    -2.34
    September
    -2.27
     September
    -2.14
    December
    -2.13
     December
    -2.08
    POSITIVE LOGITS
     April
    4.47
    April
    4.00
     spring
    3.59
     Easter
    3.58
     March
    3.58
     APRIL
    3.30
    APRIL
    3.27
    Easter
    3.17
     april
    3.14
    april
    3.02
    Activations Density 0.447%

    No Known Activations