© 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. 464
    Prev
    Next
    INDEX
    Explanations

    in connection with

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

    This neuron lights up on words signaling criminal-justice or legal-report contexts (arrests, charges, warrants, custody, connections, etc.).

    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
     Partnerships
    -0.83
    oole
    -0.78
     miro
    -0.77
    sib
    -0.77
     チェーン
    -0.75
    Rings
    -0.74
     amici
    -0.72
    Partners
    -0.71
    中でも
    -0.71
    nar
    -0.70
    POSITIVE LOGITS
     connection
    5.09
    connection
    3.89
     Connection
    3.38
    Connection
    3.28
     CONNECTION
    3.11
     connections
    3.06
    CONNECTION
    2.98
     conjunction
    2.84
     connected
    2.78
     forbindelse
    2.77
    Activations Density 0.131%

    No Known Activations