© 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. 84893
    Prev
    Next
    INDEX
    Explanations

    file headers and code

    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
    <?,
    -0.75
    рный
    -0.71
    čných
    -0.71
     menciona
    -0.69
     کرت
    -0.69
     mics
    -0.68
     bago
    -0.68
     Candice
    -0.67
     taas
    -0.67
    дёт
    -0.67
    POSITIVE LOGITS
     Br
    0.76
     OMITTED
    0.67
    制造
    0.64
    言語
    0.63
     algún
    0.63
    崎
    0.61
    enso
    0.61
     thống
    0.60
     manic
    0.60
    REACT
    0.60
    Activations Density 0.052%

    No Known Activations