© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4157
    Prev
    Next
    INDEX
    Explanations

    code definitions and version numbers

    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
     privé
    -0.69
     KJ
    -0.68
    EME
    -0.66
     Khalid
    -0.66
     nostal
    -0.66
     strix
    -0.66
    Voci
    -0.65
     FJ
    -0.65
     tratamiento
    -0.65
    wet
    -0.65
    POSITIVE LOGITS
     Eqs
    0.69
     Horoscope
    0.67
     go
    0.65
     Agility
    0.64
     main
    0.62
    Availability
    0.61
     count
    0.61
    းက
    0.60
    Hof
    0.60
     Microscopy
    0.60
    Activations Density 0.066%

    No Known Activations