© 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. 28975
    Prev
    Next
    INDEX
    Explanations

    Brun names

    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
     zoude
    -3.25
     taşlı
    -2.86
     kompeti
    -2.84
    驺
    -2.83
     rajut
    -2.73
     rokok
    -2.69
    鼱
    -2.69
    iſter
    -2.67
     kursi
    -2.63
     ingat
    -2.63
    POSITIVE LOGITS
    </b>
    2.72
    *
    2.67
     Which
    2.66
    ?
    2.64
    ↵↵
    2.58
     –
    2.55
    珖
    2.47
    tisgarh
    2.45
    心中的
    2.36
    ),
    2.33
    Activations Density 0.003%

    No Known Activations