© 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. 22-GEMMASCOPE-RES-131K
    7. 16273
    Prev
    Next
    INDEX
    Explanations

    denied or granted dates

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

    The neuron flags procedural status terms in legal citations—especially the word “Denied” when noting a petition or appeal has been refused.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ționale
    -1.06
    🛀
    -1.03
    pendente
    -0.99
     carreaux
    -0.98
     نمی
    -0.98
    ografia
    -0.98
     conçu
    -0.97
     livestream
    -0.96
     rése
    -0.95
    ﺇ
    -0.95
    POSITIVE LOGITS
     it
    1.13
     but
    1.02
     further
    0.98
     subsequent
    0.95
     later
    0.91
     subsequently
    0.88
     stesso
    0.88
     the
    0.85
     then
    0.84
     afterwards
    0.81
    Activations Density 0.041%

    No Known Activations