© 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. 48208
    Prev
    Next
    INDEX
    Explanations

    specific word pairings

    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
    桨
    -0.73
     because
    -0.71
     キャ
    -0.70
    publicPath
    -0.69
    passwd
    -0.68
    ліст
    -0.68
     park
    -0.67
     suck
    -0.67
     suction
    -0.66
     chicken
    -0.66
    POSITIVE LOGITS
    reload
    0.94
     directors
    0.84
     Reload
    0.82
    Deck
    0.78
    enio
    0.77
    nosa
    0.77
     prévenir
    0.76
    tween
    0.75
     Wildcats
    0.75
     spons
    0.75
    Activations Density 0.017%

    No Known Activations