© 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. 130521
    Prev
    Next
    INDEX
    Explanations

    cable material systems assemblies routing analysis

    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_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
     イラストレーション
    -3.00
    霂
    -2.86
    '
    -2.73
    艄
    -2.61
    llavero
    -2.56
    ’
    -2.50
    會
    -2.45
    庒
    -2.39
     continually
    -2.33
    熘
    -2.33
    POSITIVE LOGITS
    -
    2.92
    渽
    2.86
    時間を
    2.86
     jeweiligen
    2.73
     pinkish
    2.42
    殲
    2.41
    Surprisingly
    2.39
     respective
    2.36
     Если
    2.33
     dismay
    2.31
    Activations Density 0.009%

    No Known Activations