© 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. 34-GEMMASCOPE-RES-131K
    7. 25973
    Prev
    Next
    INDEX
    Explanations

    on track or within budget

    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
     repens
    -0.81
     finca
    -0.79
    úsqueda
    -0.78
    Տես
    -0.77
     mentales
    -0.76
     семина
    -0.76
     divisão
    -0.75
     mots
    -0.75
     florales
    -0.75
    ilitate
    -0.74
    POSITIVE LOGITS
     specification
    1.63
     budget
    1.38
     schedule
    1.30
    Specification
    1.26
     Specification
    1.19
    specification
    1.16
     specifications
    1.16
     spec
    1.14
     protocol
    1.13
     quota
    1.09
    Activations Density 0.055%

    No Known Activations