© 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. 41665
    Prev
    Next
    INDEX
    Explanations

    code blocks and event handlers

    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
     a
    -1.97
     which
    -1.94
     their
    -1.84
     actionTypes
    -1.58
     \
    -1.52
     userModel
    -1.48
     «
    -1.44
     сфере
    -1.43
     climático
    -1.35
     пределах
    -1.34
    POSITIVE LOGITS
    bolsa
    1.84
    .
    1.51
    DNEY
    1.50
    Cubit
    1.48
     ständig
    1.48
     encender
    1.46
     ingresar
    1.41
     detener
    1.41
     llenar
    1.40
    vampire
    1.39
    Activations Density 0.003%

    No Known Activations