© 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. 10-GEMMASCOPE-RES-131K
    7. 1870
    Prev
    Next
    INDEX
    Explanations

    PIN, stairs, VU, WMS

    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_10/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
    𝘰
    -2.42
     speculated
    -2.23
     jokingly
    -2.13
    搽
    -2.11
    ?"
    -2.09
     शुर
    -2.05
    ā
    -2.00
     be
    -1.98
     «
    -1.97
    ed
    -1.96
    POSITIVE LOGITS
     stairs
    3.16
     haja
    2.34
     reclamar
    2.34
    擽
    2.33
     bús
    2.33
    ází
    2.28
     quí
    2.28
    狴
    2.27
     pantalón
    2.25
     flesta
    2.25
    Activations Density 0.001%

    No Known Activations