© 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. 15070
    Prev
    Next
    INDEX
    Explanations

    Cross-appellant, Plaintiff, corporation

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

    The neuron flags the numeric volume and page‐number tokens that appear in legal case citations.

    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
     of
    -1.86
    也将
    -1.51
     these
    -1.16
     also
    -1.13
     wiederum
    -1.10
     that
    -1.04
    Explicación
    -1.03
     etc
    -1.02
     such
    -1.02
     any
    -1.02
    POSITIVE LOGITS
    ΑΡ
    1.12
     Besoin
    1.11
     Réponses
    1.08
     Euró
    1.06
     Autres
    1.05
    МИ
    1.03
    osoba
    1.03
     květ
    1.02
     วัน
    1.02
     CONTENTS
    1.02
    Activations Density 0.063%

    No Known Activations