© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83778
    Prev
    Next
    INDEX
    Explanations

    Legal names and initials

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

    It detects the volume-number/reporter-abbreviation components of legal case citations (e.g. “123 F.2d 456” or “J. 789”).

    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
     skup
    -0.95
     sonre
    -0.93
    Qué
    -0.90
    fokus
    -0.89
     família
    -0.88
     firmy
    -0.86
     '/';
    -0.85
     ll
    -0.85
    Auch
    -0.83
     estatu
    -0.83
    POSITIVE LOGITS
     valsty
    0.91
    fizierung
    0.90
    J
    0.90
    ようですが
    0.88
     veldig
    0.88
     forskjellige
    0.80
     octavia
    0.79
     ロン
    0.78
     opravdu
    0.77
     моги
    0.77
    Activations Density 0.049%

    No Known Activations