© 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. 2384
    Prev
    Next
    INDEX
    Explanations

    guaranteed rights and protections

    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
    gtk
    -0.93
     сведения
    -0.89
    antası
    -0.86
    zaamheid
    -0.84
    riever
    -0.83
     abdomen
    -0.81
    🆔
    -0.79
    utare
    -0.79
     economies
    -0.78
     attrs
    -0.78
    POSITIVE LOGITS
    guar
    2.30
     guaranteed
    2.17
     guarantee
    2.14
     protections
    2.14
     protected
    2.11
     guarantees
    2.09
     protect
    2.09
     protects
    2.03
     protection
    2.02
     protecting
    1.99
    Activations Density 0.047%

    No Known Activations