© 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. 31828
    Prev
    Next
    INDEX
    Explanations

    code structure and imports

    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
     employes
    -0.80
     Javan
    -0.79
     Frases
    -0.75
     ingeniería
    -0.75
    锲
    -0.73
    stoß
    -0.72
    اعدة
    -0.72
     quia
    -0.72
    Tomorrow
    -0.72
    tomorrow
    -0.72
    POSITIVE LOGITS
     strengths
    0.79
     चे
    0.72
     strength
    0.71
    卍
    0.71
    召
    0.71
     launch
    0.69
    ('-'
    0.69
     Mohammed
    0.68
    험
    0.68
    ink
    0.68
    Activations Density 0.022%

    No Known Activations