© 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. 110864
    Prev
    Next
    INDEX
    Explanations

    on top of / above

    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
    kovi
    -0.85
     Schiff
    -0.84
    ucson
    -0.82
    niska
    -0.80
    uevos
    -0.76
    силання
    -0.76
     kdy
    -0.76
     Oval
    -0.75
     водой
    -0.73
    bondale
    -0.73
    POSITIVE LOGITS
     atop
    4.16
     encima
    3.31
     поверх
    2.64
    atop
    2.42
     сверху
    2.31
    OnTop
    2.27
     on
    2.27
    の上に
    2.11
     top
    2.02
     boven
    1.88
    Activations Density 0.138%

    No Known Activations