© 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. 10-GEMMASCOPE-RES-131K
    7. 71426
    Prev
    Next
    INDEX
    Explanations

    Petitioner versus

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

    The neuron identifies the “v. <volume> <page>” pattern in legal case citations (i.e. the volume number, reporter abbreviation “v.” and page number).

    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
     himself
    -1.51
    bezpiecz
    -1.36
     pravi
    -1.27
     will
    -1.26
     from
    -1.25
    äden
    -1.24
    今朝
    -1.23
     cioè
    -1.23
     ajang
    -1.23
    ｵ
    -1.20
    POSITIVE LOGITS
     its
    1.85
     themselves
    1.63
    its
    1.48
    </strong>
    1.28
     their
    1.23
    see
    1.21
    -
    1.13
     swojej
    1.12
     website
    1.11
     thier
    1.11
    Activations Density 0.272%

    No Known Activations