© 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. 37821
    Prev
    Next
    INDEX
    Explanations

    author metadata

    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
    ālā
    -0.96
     intolerable
    -0.91
     inconsist
    -0.85
     シャンプー
    -0.82
    copus
    -0.82
     '-'
    -0.82
     spectroscopic
    -0.81
     viață
    -0.81
     Linkedin
    -0.79
     proportioned
    -0.79
    POSITIVE LOGITS
    艘
    0.73
     sangat
    0.73
     maravilh
    0.72
     zah
    0.71
    。。
    0.71
     кампа
    0.71
     acompan
    0.71
     Farbe
    0.71
    石油
    0.71
    BR
    0.70
    Activations Density 0.121%

    No Known Activations