© 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. 80954
    Prev
    Next
    INDEX
    Explanations

    software and license versions

    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
    raisemb
    -0.68
    razit
    -0.67
     ciepła
    -0.66
     getContent
    -0.66
    TokenNameR
    -0.66
     sạc
    -0.65
     białe
    -0.65
    DotNetBar
    -0.65
    Sum
    -0.65
     первых
    -0.65
    POSITIVE LOGITS
    大于
    0.81
    Sharper
    0.78
     =[
    0.73
    Cele
    0.73
     krist
    0.71
     imparti
    0.69
     inve
    0.67
     secu
    0.67
     maint
    0.66
    Kok
    0.66
    Activations Density 0.069%

    No Known Activations