© 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. 90129
    Prev
    Next
    INDEX
    Explanations

    memorials and remembrance

    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
     congratulate
    -0.93
     congratulated
    -0.91
     divertidas
    -0.83
    IntoConstraints
    -0.82
     invitados
    -0.82
    amide
    -0.82
     ögon
    -0.80
     verste
    -0.79
    coins
    -0.77
    hydrogen
    -0.77
    POSITIVE LOGITS
     memorial
    3.27
     tribute
    2.53
     remembrance
    2.38
     memory
    2.33
     posthum
    2.28
     memorials
    2.27
    memorial
    2.13
     honoring
    2.09
     Memorial
    2.08
     remembering
    2.06
    Activations Density 0.044%

    No Known Activations