© 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. 10-GEMMASCOPE-RES-131K
    7. 123771
    Prev
    Next
    INDEX
    Explanations

    Maharaj, Kag, Ute, Eug, ppc, zsh, udf, Kamp

    np_acts-logits-general · gemini-2.5-flash-lite

    words containing the letter sequence "ag" followed by a vowel, particularly in scientific or technical terminology (like "Kagomé", "Drosophila", "gladiatorial", "UDF").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -2.78
    
    -2.52
     scrutin
    -2.50
    ścić
    -2.41
    zação
    -2.41
     helicóptero
    -2.39
    ].
    -2.33
    ဴ
    -2.33
    莚
    -2.22
    蒾
    -2.20
    POSITIVE LOGITS
    筇
    3.22
    嵛
    3.00
    慙
    2.84
     получила
    2.80
    .
    2.72
    塒
    2.64
    屺
    2.53
    深的
    2.52
     łóż
    2.45
    堙
    2.42
    Activations Density 0.066%

    No Known Activations