© 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. 98037
    Prev
    Next
    INDEX
    Explanations

    dialogs and modals

    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
     appropriation
    -0.83
    inal
    -0.75
    ائص
    -0.75
    ęcia
    -0.73
    עות
    -0.72
    vimento
    -0.72
     keputusan
    -0.71
    ⋈
    -0.71
    reté
    -0.71
    making
    -0.69
    POSITIVE LOGITS
     example
    1.10
    myModal
    1.05
     large
    0.99
    large
    0.93
    example
    0.91
    Large
    0.87
    なくても
    0.84
     Large
    0.80
     delete
    0.80
     где
    0.79
    Activations Density 0.005%

    No Known Activations