© 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. 108446
    Prev
    Next
    INDEX
    Explanations

    assist or facilitate actions

    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
    诡异
    -1.34
     alarma
    -1.32
     membantu
    -1.32
     nabízí
    -1.28
     gorro
    -1.27
     chaleco
    -1.27
     taches
    -1.27
    pueden
    -1.25
    después
    -1.24
     câbles
    -1.24
    POSITIVE LOGITS
     to
    3.02
     with
    2.13
    fully
    1.43
     them
    1.42
     build
    1.41
     us
    1.40
     make
    1.38
     ensure
    1.37
     in
    1.35
    www
    1.33
    Activations Density 0.028%

    No Known Activations