© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8906
    Prev
    Next
    INDEX
    Explanations

    lives claimed or cost

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

    The neuron detects mentions of deaths or casualties—particularly words like “death,” “claimed,” and “lives” in the context of counting fatalities.

    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
     are
    -2.22
     such
    -1.45
     ,,
    -1.42
     techniques
    -1.40
    –
    -1.37
     mentre
    -1.30
    ють
    -1.30
     it
    -1.30
    ца
    -1.29
    }$
    -1.27
    POSITIVE LOGITS
     cafetería
    1.37
    帮你
    1.36
     yaklaşık
    1.28
    ⓿
    1.27
    峦
    1.27
     femininas
    1.27
    Цент
    1.26
     preciosa
    1.24
    魨
    1.23
    (*^^
    1.22
    Activations Density 0.058%

    No Known Activations