© 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. 29202
    Prev
    Next
    INDEX
    Explanations

    ways of doing things

    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
    赑
    -2.67
    辗
    -2.44
     bisschen
    -2.44
     leão
    -2.36
     unicórnio
    -2.14
    完美的
    -2.13
    ギュア
    -2.11
     lanzó
    -2.09
     famoso
    -2.09
    　↓
    -2.08
    POSITIVE LOGITS
    as
    2.89
    ia
    2.38
    el
    2.36
    ne
    2.36
    ite
    2.25
    if
    2.22
    ds
    2.22
     They
    2.19
    os
    2.16
    ani
    2.16
    Activations Density 0.010%

    No Known Activations