© 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. 110985
    Prev
    Next
    INDEX
    Explanations

    think and talk about

    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
    ⊰
    -0.77
    czegó
    -0.76
     актриса
    -0.75
    𝐜
    -0.73
     Takt
    -0.73
     concentrates
    -0.73
    Its
    -0.73
    Magn
    -0.71
     baza
    -0.70
     στε
    -0.70
    POSITIVE LOGITS
     things
    2.16
     it
    2.08
     through
    1.77
     out
    1.52
     this
    1.41
    Things
    1.33
     Things
    1.22
    things
    1.22
     igenom
    1.19
     это
    1.14
    Activations Density 0.022%

    No Known Activations