© 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. 92462
    Prev
    Next
    INDEX
    Explanations

    Bruce, Bruno, Braley, Bruhat

    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
    ativement
    -0.80
     Gebühren
    -0.79
    lou
    -0.79
    peth
    -0.79
     WL
    -0.77
    gebras
    -0.75
     traversed
    -0.75
     else
    -0.75
    cto
    -0.75
    mil
    -0.75
    POSITIVE LOGITS
    Bru
    0.82
    orited
    0.77
     retrovisor
    0.77
     stimm
    0.71
    zipped
    0.71
    讴
    0.70
    Br
    0.70
     samen
    0.69
     בג
    0.69
     Bru
    0.69
    Activations Density 0.024%

    No Known Activations