© 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. 22-GEMMASCOPE-RES-131K
    4. 69141
    Prev
    Next
    INDEX
    Explanations

    growing up and getting older

    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
    ↵↵
    -1.17
     posed
    -1.14
     for
    -1.13
     system
    -1.13
     motivates
    -1.06
     if
    -1.04
     offered
    -1.02
     given
    -0.96
     of
    -0.96
     between
    -0.94
    POSITIVE LOGITS
     almofada
    1.27
     adolescence
    1.22
    และ
    1.22
     jednego
    1.21
    pielen
    1.20
     adulthood
    1.16
     and
    1.12
    くなり
    1.11
     versões
    1.11
     dovol
    1.09
    Activations Density 0.015%

    No Known Activations