© 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. 34-GEMMASCOPE-RES-131K
    4. 117876
    Prev
    Next
    INDEX
    Explanations

    bail and detention

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

    The neuron detects mentions of being released on bond––i.e. “released on a $___ bond” phrasing.

    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
    неров
    -0.93
     sequins
    -0.85
     Tomlinson
    -0.83
     Apprentices
    -0.81
     Onze
    -0.81
     BLL
    -0.80
    탬
    -0.79
     Fines
    -0.78
     dlc
    -0.78
     Ith
    -0.77
    POSITIVE LOGITS
     bail
    1.49
     pretrial
    1.24
     detention
    1.23
     Bail
    1.20
     release
    1.15
    Bail
    1.14
     flight
    1.11
    release
    1.09
     Release
    1.08
     danger
    1.07
    Activations Density 0.023%

    No Known Activations