© 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. 73681
    Prev
    Next
    INDEX
    Explanations

    Ionic navigation and UI elements

    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
     androidx
    -0.82
     réussi
    -0.81
     Router
    -0.78
    DIPSETTING
    -0.77
    λώ
    -0.77
     võib
    -0.77
    .'</
    -0.75
     路
    -0.75
    stereotype
    -0.73
     Pries
    -0.73
    POSITIVE LOGITS
     Turbulence
    0.77
     open
    0.77
     opened
    0.73
     Hoff
    0.72
    項目
    0.71
     imo
    0.70
     отсут
    0.70
    simos
    0.70
    に入り
    0.69
     testSet
    0.69
    Activations Density 0.008%

    No Known Activations