© 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. 33992
    Prev
    Next
    INDEX
    Explanations

    Denied, Granted followed by month

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

    The neuron detects legal procedural headings and status phrases (e.g. “Argued,” “Decided,” “Writ of Certiorari Denied,” “Review Granted,” etc.).

    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
    aneity
    -1.16
     mentre
    -1.15
     consultato
    -1.11
    dehyde
    -1.07
    ParallelGroup
    -1.06
    aria
    -1.05
    Economía
    -1.03
     straff
    -1.02
     you
    -1.02
     Infór
    -1.02
    POSITIVE LOGITS
    ,
    1.10
     and
    1.05
     thereafter
    0.98
    ciri
    0.96
     except
    0.96
    жить
    0.95
     допомогти
    0.94
    —
    0.94
    nių
    0.93
     metabolites
    0.93
    Activations Density 0.042%

    No Known Activations