© 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. 12376
    Prev
    Next
    INDEX
    Explanations

    business card, validation, predator

    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
    <bos>
    -1.80
     this
    -1.57
    Different
    -1.55
     to
    -1.50
    お楽しみに
    -1.42
     diferentes
    -1.41
    有難
    -1.31
     it
    -1.31
    。"
    -1.30
     gevallen
    -1.30
    POSITIVE LOGITS
    k
    1.48
    ないように
    1.28
     всі
    1.23
     chyba
    1.21
    c
    1.20
    HOSTS
    1.18
     $_=
    1.13
     ऐसे
    1.13
     Krzysz
    1.13
     brasile
    1.13
    Activations Density 8.601%

    No Known Activations