© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2517
    Prev
    Next
    INDEX
    Explanations

    months and seasons

    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
     June
    -1.16
    JUNE
    -1.05
     July
    -1.03
    June
    -1.01
     يونيو
    -0.90
    July
    -0.85
    AUGUST
    -0.85
     JUNE
    -0.81
     ию
    -0.75
    august
    -0.73
    POSITIVE LOGITS
     January
    1.84
    January
    1.77
     December
    1.71
    December
    1.65
     Christmas
    1.48
     JANUARY
    1.46
     November
    1.38
     january
    1.37
     décembre
    1.27
     christmas
    1.24
    Activations Density 0.026%

    No Known Activations