© 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. 38300
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
    وتی
    -0.79
    OrderItem
    -0.73
     marvellous
    -0.69
     centrale
    -0.69
     俺
    -0.68
     suffices
    -0.68
    ة
    -0.67
    げ
    -0.67
     perquè
    -0.66
    יפ
    -0.65
    POSITIVE LOGITS
     July
    1.48
     January
    1.45
    January
    1.40
    July
    1.40
     October
    1.34
    April
    1.25
     April
    1.24
    October
    1.22
     JANUARY
    1.21
    Jul
    1.15
    Activations Density 0.019%

    No Known Activations