© 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. 22-GEMMASCOPE-RES-131K
    7. 13242
    Prev
    Next
    INDEX
    Explanations

    justice department

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

    The neuron flags tokens that occur as isolated “stand‐alone” items or headings—i.e. single words (often link anchor text or section titles) appearing by themselves on a line.

    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
    Either
    -1.22
    pakah
    -1.20
     ſever
    -1.14
    uthor
    -1.06
     también
    -1.05
     obé
    -1.05
     Either
    -1.05
    性が
    -1.04
    CUSS
    -1.03
    んですね
    -1.00
    POSITIVE LOGITS
    もあって
    1.03
    。』
    1.02
    内容は
    0.99
    だが
    0.96
    問題は
    0.91
     کردند
    0.88
    がありますが
    0.88
    写真は
    0.88
    ),
    0.86
     QtWidgets
    0.85
    Activations Density 0.010%

    No Known Activations