© 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. 90086
    Prev
    Next
    INDEX
    Explanations

    pairing behaviour, span template, Sandy railway

    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
    Hahaha
    -0.88
    리는
    -0.77
    Unemployment
    -0.72
     treino
    -0.70
     seguir
    -0.69
    ement
    -0.69
     сталь
    -0.68
    チー
    -0.66
    iai
    -0.66
    ål
    -0.66
    POSITIVE LOGITS
    onChanged
    1.27
    Dropdown
    1.02
    dropdown
    0.90
     dropdown
    0.87
     value
    0.84
    ностях
    0.84
    value
    0.83
     venit
    0.82
     ライフ
    0.81
     Dropdown
    0.79
    Activations Density 0.001%

    No Known Activations