© 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. 6900
    Prev
    Next
    INDEX
    Explanations

    shot by gunmen, by unknown, by police

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

    This neuron activates on numeric tokens (multi‐digit numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     hostages
    -1.00
    victim
    -0.95
     victims
    -0.91
     needed
    -0.83
     captives
    -0.82
    ただし
    -0.81
     Victims
    -0.80
    Manufacturer
    -0.79
     моз
    -0.79
     ſu
    -0.77
    POSITIVE LOGITS
     jealous
    1.64
     angry
    1.53
     envious
    1.14
    angry
    1.14
     hungry
    1.13
     enraged
    1.11
     furious
    1.05
     desconocido
    1.04
     unidentified
    0.98
     drunk
    0.97
    Activations Density 0.069%

    No Known Activations