© 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. 98100
    Prev
    Next
    INDEX
    Explanations

    date strings

    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
     Peach
    -1.31
     peaches
    -1.30
     peach
    -1.26
    Peach
    -1.14
    peach
    -1.04
     strawberries
    -1.00
     cherries
    -0.99
     Peaches
    -0.99
     CEST
    -0.97
     apricots
    -0.97
    POSITIVE LOGITS
     December
    1.03
    December
    1.02
    November
    0.94
     décembre
    0.93
     winter
    0.91
     novembre
    0.88
     DECEMBER
    0.88
     chestnuts
    0.88
     November
    0.87
    Cran
    0.86
    Activations Density 0.026%

    No Known Activations