© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108113
    Prev
    Next
    INDEX
    Explanations

    code keywords and values

    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_34/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
     prédé
    -1.48
     acrylique
    -1.48
    properly
    -1.47
    helping
    -1.45
     poêle
    -1.41
    offering
    -1.41
     zobac
    -1.40
     niebieski
    -1.39
     demandes
    -1.39
     conséquent
    -1.39
    POSITIVE LOGITS
     false
    2.44
     null
    1.90
     true
    1.89
    false
    1.88
     False
    1.76
     "",
    1.73
    true
    1.69
     new
    1.69
     None
    1.46
     although
    1.45
    Activations Density 0.012%

    No Known Activations