© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67392
    Prev
    Next
    INDEX
    Explanations

    studies completed and returned

    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_22/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
     religieuses
    -1.24
     chré
    -1.16
    swar
    -1.07
     would
    -1.04
    asnya
    -0.98
     berlaku
    -0.98
     dilan
    -0.95
    様が
    -0.94
     kişinin
    -0.94
    治愈
    -0.94
    POSITIVE LOGITS
    ֶּ
    1.30
    ּוֹ
    1.20
    porque
    1.20
    Люди
    1.16
     who
    1.14
    เพราะ
    1.12
    igth
    1.11
    ֵּ
    1.09
    ַּ
    1.08
     completed
    1.07
    Activations Density 0.263%

    No Known Activations