© 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. 49881
    Prev
    Next
    INDEX
    Explanations

    Starts of lists and sentences

    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
     mauvaise
    -0.85
    elve
    -0.80
     color
    -0.78
     déroule
    -0.74
    ("$.
    -0.72
    jv
    -0.72
    ajaan
    -0.71
     tristesse
    -0.71
     chamar
    -0.71
     Gala
    -0.71
    POSITIVE LOGITS
    cado
    0.82
    読む
    0.78
    ÁN
    0.78
    ϱ
    0.72
     instance
    0.71
    σης
    0.71
    produksi
    0.71
    zdro
    0.70
    SearchBar
    0.69
     intérprete
    0.69
    Activations Density 0.000%

    No Known Activations