© 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. 2123
    Prev
    Next
    INDEX
    Explanations

    court cases or legal documents

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

    This neuron fires on name‐like tokens—that is, proper nouns, class/file/variable identifiers, and other mixed-case “names.”

    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
    Although
    -0.89
    Since
    -0.88
     kaybet
    -0.86
    青森
    -0.86
    麗
    -0.85
     República
    -0.84
    Depending
    -0.83
     Since
    -0.82
    fromnode
    -0.82
     AWESOME
    -0.80
    POSITIVE LOGITS
    unk
    0.92
    probably
    0.89
    stru
    0.88
     stru
    0.84
    LOD
    0.84
    siempre
    0.82
    wins
    0.82
    纸
    0.81
    always
    0.81
     resultat
    0.81
    Activations Density 0.001%

    No Known Activations