© 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. 83063
    Prev
    Next
    INDEX
    Explanations

    stage and performance

    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
    晖
    -0.88
    禧
    -0.83
    inesh
    -0.82
     getLayout
    -0.82
    谙
    -0.82
    pushd
    -0.81
    xff
    -0.81
    ява
    -0.80
     møte
    -0.79
    weiler
    -0.79
    POSITIVE LOGITS
     character
    1.33
     characters
    1.24
     truthful
    1.09
     choices
    1.09
     belie
    1.08
    人物
    1.03
     onstage
    1.02
     playable
    1.01
     believable
    0.97
    表演
    0.96
    Activations Density 0.006%

    No Known Activations