© 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. 34-GEMMASCOPE-RES-131K
    7. 77472
    Prev
    Next
    INDEX
    Explanations

    ryan followed by surname

    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
    s
    -0.94
     broad
    -0.91
     Zitron
    -0.89
    שת
    -0.84
     assunto
    -0.83
     ου
    -0.81
     him
    -0.80
     fapt
    -0.79
    g
    -0.79
    gun
    -0.78
    POSITIVE LOGITS
    nair
    1.08
     Gosling
    1.02
     Рей
    1.01
    Air
    0.99
    IJ
    0.97
    ulaires
    0.92
    GroupBy
    0.92
    できるので
    0.91
    izza
    0.90
     zweier
    0.89
    Activations Density 0.003%

    No Known Activations