© 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. 83377
    Prev
    Next
    INDEX
    Explanations

    about you and them

    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
     nocturne
    -1.00
    onnaise
    -0.99
    níků
    -0.98
     gurus
    -0.98
     adieu
    -0.98
     douche
    -0.93
     mirador
    -0.92
     hoga
    -0.91
     peru
    -0.91
     secreta
    -0.91
    POSITIVE LOGITS
     you
    3.06
     their
    2.64
     your
    2.03
     customers
    1.76
    Their
    1.66
     customer
    1.57
     YOU
    1.52
     us
    1.47
     ihren
    1.45
     its
    1.44
    Activations Density 0.028%

    No Known Activations