© 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. 22-GEMMASCOPE-RES-131K
    7. 27357
    Prev
    Next
    INDEX
    Explanations

    code : separator : value

    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_22/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
    )=>{
    -1.02
    のですか
    -0.98
    änk
    -0.96
     juzg
    -0.93
    の前
    -0.92
    tilen
    -0.91
     enchufe
    -0.91
     dáms
    -0.90
    ませんが
    -0.90
    elesai
    -0.90
    POSITIVE LOGITS
     to
    0.91
    ('
    0.87
     those
    0.87
    <eos>
    0.86
    かで
    0.84
     tewas
    0.81
    atie
    0.80
     affections
    0.80
     contraire
    0.79
    warte
    0.79
    Activations Density 0.003%

    No Known Activations