© 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. 84727
    Prev
    Next
    INDEX
    Explanations

    criminal incident arrest violation

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

    The neuron specializes in spotting mentions of criminal charges, trials, and related legal‐proceeding terminology.

    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
    murder
    -1.06
     murderer
    -1.01
     murder
    -1.01
     murdered
    -0.87
     oftentimes
    -0.84
     even
    -0.84
    avatars
    -0.84
     talked
    -0.83
     murderers
    -0.82
     murders
    -0.82
    POSITIVE LOGITS
     incident
    1.14
     incidents
    1.05
    TM
    1.04
     allegations
    1.04
     Airport
    1.00
     Incident
    0.97
     airport
    0.96
    δα
    0.94
     zdar
    0.92
     assault
    0.91
    Activations Density 0.041%

    No Known Activations