© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10970
    Prev
    Next
    INDEX
    Explanations

    submission dates

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

    The neuron flags the procedural metadata lines in legal opinions—especially the “Submitted/Argued on” date and case‐filing details.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     The
    -1.65
    上官
    -1.65
    之路
    -1.65
     mantra
    -1.59
     $>
    -1.58
    粉色
    -1.56
     могут
    -1.55
    }
    -1.55
     biß
    -1.54
    椰
    -1.54
    POSITIVE LOGITS
    </h3>
    2.09
    1
    1.82
     asesor
    1.70
    \
    1.65
    稣
    1.63
     handful
    1.63
     駅前
    1.62
     sequentially
    1.60
     pios
    1.58
     こう
    1.56
    Activations Density 0.015%

    No Known Activations