© 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. 103070
    Prev
    Next
    INDEX
    Explanations

    google api discovery and services

    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
     slide
    -0.84
    сні
    -0.82
     in
    -0.82
    推送
    -0.80
     most
    -0.78
    PF
    -0.78
     Life
    -0.78
     with
    -0.77
     sleek
    -0.77
     life
    -0.76
    POSITIVE LOGITS
    discovery
    0.92
     méthodes
    0.91
    released
    0.89
    considering
    0.88
    haa
    0.86
    discovered
    0.85
     SERVICE
    0.85
    discover
    0.83
    disco
    0.82
    waffle
    0.82
    Activations Density 0.023%

    No Known Activations