© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99055
    Prev
    Next
    INDEX
    Explanations

    names of justices

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

    The neuron strongly fires on court opinion headings—specifically on the title tokens “Justice” or “Justices” (i.e. judge‐designation terms).

    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
    哢
    -2.58
     vyroben
    -2.22
    </strong>
    -2.09
    咾
    -2.08
     dekoratif
    -2.08
     mantenga
    -2.08
    嫗
    -2.03
     ブラウス
    -2.02
     juſt
    -1.98
    …)
    -1.95
    POSITIVE LOGITS
    In
    2.77
     of
    2.55
    $
    2.28
    O
    2.09
    I
    2.02
    U
    2.02
     では
    1.98
    As
    1.93
    An
    1.91
    On
    1.89
    Activations Density 0.006%

    No Known Activations