© 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. 33594
    Prev
    Next
    INDEX
    Explanations

    legal justice, store fronts, comments, cuts, why, networks, images, maximum

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

    The neuron fires strongly on content‐bearing “topic” words (key nouns or terms that signal the subject of a passage).

    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
     Journ
    -0.98
     traktor
    -0.97
     demokra
    -0.97
     ira
    -0.96
    geschlossen
    -0.95
    ٱ
    -0.95
     Israël
    -0.94
     busi
    -0.93
    Rusia
    -0.93
    再见
    -0.92
    POSITIVE LOGITS
     of
    1.07
    II
    0.98
     that
    0.95
     try
    0.92
     એ
    0.91
     II
    0.91
     für
    0.90
     ermöglicht
    0.90
     not
    0.90
    MessageOf
    0.90
    Activations Density 0.066%

    No Known Activations