© 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. 102593
    Prev
    Next
    INDEX
    Explanations

    add action

    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
     but
    -0.87
    olites
    -0.75
     kvä
    -0.72
    有什么
    -0.70
     števil
    -0.70
     房子
    -0.69
    Because
    -0.69
    isShow
    -0.69
    BRACE
    -0.68
    atiana
    -0.68
    POSITIVE LOGITS
     action
    2.42
    Action
    2.06
    action
    2.05
     Action
    2.02
    ACTION
    1.77
     ACTION
    1.74
    アクション
    1.67
     acción
    1.63
     actions
    1.51
    actions
    1.50
    Activations Density 0.009%

    No Known Activations