© 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. 78870
    Prev
    Next
    INDEX
    Explanations

    We have

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

    The neuron flags formal legal–opinion vocabulary—terms and phrases typical of court briefs and judicial opinions.

    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
    既存
    -0.91
     wspania
    -0.85
    あくまで
    -0.85
     urodz
    -0.85
     mancha
    -0.85
     hembra
    -0.84
    内装
    -0.83
    機動
    -0.82
     yüzde
    -0.82
    formazioni
    -0.81
    POSITIVE LOGITS
     decided
    0.89
     appearing
    0.88
     we
    0.88
    ể
    0.86
    Disposition
    0.86
     ладо
    0.84
     deciding
    0.84
     appear
    0.83
     zub
    0.82
     our
    0.81
    Activations Density 0.037%

    No Known Activations