© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99366
    Prev
    Next
    INDEX
    Explanations

    democratic development

    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
    periodo
    -0.84
     luogo
    -0.81
     dette
    -0.80
    красивые
    -0.79
     quam
    -0.78
    mercados
    -0.77
    UserController
    -0.77
    permalink
    -0.76
    нього
    -0.75
    chatron
    -0.74
    POSITIVE LOGITS
    Inside
    0.98
    inside
    0.89
     שלנו
    0.83
     Inside
    0.82
    нился
    0.81
     ajuta
    0.80
     ważne
    0.79
    ĩ
    0.79
    Веду
    0.79
    ()}}
    0.77
    Activations Density 0.000%

    No Known Activations