© 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. 90658
    Prev
    Next
    INDEX
    Explanations

    creation date and author comments

    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
     the
    -1.71
     âmes
    -1.68
     acepción
    -1.60
     położ
    -1.57
     були
    -1.53
     journalistes
    -1.52
    ÑOS
    -1.51
     bénévoles
    -1.47
     sagt
    -1.45
    ...
    -1.45
    POSITIVE LOGITS
    </h2>
    1.70
    (":");
    1.58
    adec
    1.52
    >
    1.51
    ximadamente
    1.50
     اي
    1.49
     comprobar
    1.43
     båda
    1.42
     fyra
    1.40
     gemens
    1.40
    Activations Density 0.029%

    No Known Activations