© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63297
    Prev
    Next
    INDEX
    Explanations

    digital age and world

    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
    ELING
    -0.90
     singular
    -0.79
     viable
    -0.78
     practices
    -0.77
     traditional
    -0.75
     aplikacji
    -0.75
    覚え
    -0.75
     Gesetzes
    -0.75
    тием
    -0.75
     typical
    -0.75
    POSITIVE LOGITS
     world
    2.45
     era
    1.69
     age
    1.65
     világ
    1.57
     mundo
    1.51
     wereld
    1.45
    world
    1.40
    世界
    1.31
     düny
    1.31
     época
    1.28
    Activations Density 0.033%

    No Known Activations