© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67467
    Prev
    Next
    INDEX
    Explanations

    tragic news and loss

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

    The neuron activates on words and phrases signaling death notices or expressions of tragic loss and mourning.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    :
    -1.29
     if
    -1.20
    DeclareMath
    -1.16
    !
    -1.13
    ?
    -1.02
     Tamil
    -0.98
     espirituales
    -0.97
    藜
    -0.97
     färg
    -0.95
    готавли
    -0.95
    POSITIVE LOGITS
     Meksi
    1.27
     konserv
    1.23
     another
    1.16
     happened
    1.16
     cellspacing
    1.11
     vokal
    1.11
     perda
    1.11
    Reparto
    1.11
     traged
    1.10
     Этот
    1.10
    Activations Density 0.026%

    No Known Activations