© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103303
    Prev
    Next
    INDEX
    Explanations

    murder and its victims

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

    The neuron strongly activates on explicit references to murder or closely related crime terms.

    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
    。
    -2.83
    didSet
    -2.81
    )++;
    -2.30
    ⬯
    -2.25
    ۔
    -2.22
     }));
    -2.20
    plevel
    -2.17
     onCreateView
    -2.17
    ।
    -2.17
     onOptions
    -2.14
    POSITIVE LOGITS
    ↵
    4.47
    .
    2.81
     Beschluss
    2.08
    zelfde
    2.05
     növény
    1.99
     vektör
    1.96
     yaptı
    1.95
     The
    1.92
     получил
    1.84
     sırasında
    1.83
    Activations Density 0.014%

    No Known Activations