© 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. 28449
    Prev
    Next
    INDEX
    Explanations

    era of

    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
    薷
    -2.61
    憮
    -2.61
    鰨
    -2.56
     oči
    -2.53
    昻
    -2.44
    の概要
    -2.39
    ︕
    -2.38
    medriver
    -2.33
    鉏
    -2.27
    meditation
    -2.23
    POSITIVE LOGITS
     of
    3.23
    (
    2.91
    .
    2.52
    e
    2.28
    f
    2.27
    c
    2.27
    So
    2.23
    h
    2.22
     
    2.22
     его
    2.22
    Activations Density 0.012%

    No Known Activations