© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38769
    Prev
    Next
    INDEX
    Explanations

    RIP and birthdays

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects occurrences of the three‐letter sequence “RIP” (especially as an uppercase acronym).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ጢ
    -2.47
     でも
    -2.27
    engeance
    -2.19
     ก็
    -2.09
    chengladbach
    -2.06
    輅
    -2.02
    珢
    -1.99
     usual
    -1.98
    薷
    -1.98
    <bos>
    -1.95
    POSITIVE LOGITS
    ↵
    3.39
    a
    2.98
    which
    2.31
    퐹
    2.25
    
    1.97
    e
    1.92
     verhaal
    1.90
     was
    1.88
    哪儿
    1.88
    i
    1.88
    Activations Density 0.001%

    No Known Activations