© 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. 25765
    Prev
    Next
    INDEX
    Explanations

    puducherry express

    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
     distinct
    -0.85
    Promise
    -0.81
     operacional
    -0.80
     kirch
    -0.79
     咲
    -0.77
     always
    -0.77
     seines
    -0.73
    缀
    -0.73
     pantalón
    -0.73
     feasible
    -0.72
    POSITIVE LOGITS
    飒
    0.88
    avocat
    0.82
    checs
    0.81
     glucos
    0.81
    ourced
    0.81
    jected
    0.80
     női
    0.80
     inappro
    0.80
     cualquier
    0.80
    ienka
    0.79
    Activations Density 0.000%

    No Known Activations