© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62861
    Prev
    Next
    INDEX
    Explanations

    law of the case

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

    The neuron activates strongly on formal legal enforcement clauses—particularly quoted “enforcement of” provisions (e.g. sections of an executive order).

    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
     really
    -0.94
     being
    -0.85
     befür
    -0.82
     specific
    -0.78
     urged
    -0.77
    蔭
    -0.77
     refused
    -0.76
    谘
    -0.76
     furthering
    -0.76
     continual
    -0.75
    POSITIVE LOGITS
    dding
    1.22
    unicaciones
    1.10
    carus
    1.09
    alers
    1.05
    llac
    1.03
    nières
    0.98
    Confidence
    0.94
    athed
    0.94
    mming
    0.92
    vermectin
    0.92
    Activations Density 0.027%

    No Known Activations