© 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. 72066
    Prev
    Next
    INDEX
    Explanations

    entities and their descriptions

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

    The neuron fires strongly on the main topic nouns (key technical objects or entities) in a text.

    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
     \&
    -1.20
     \
    -1.01
    瘡
    -1.00
    евра
    -0.96
    іга
    -0.93
    autoreleasepool
    -0.93
     However
    -0.92
    omenti
    -0.92
     also
    -0.91
     ร์
    -0.91
    POSITIVE LOGITS
     segments
    1.17
     sayfası
    1.11
     elements
    1.05
    ставьте
    1.04
     parts
    1.03
     Miß
    0.99
     poud
    0.96
    ﹔
    0.96
     promover
    0.95
     subunit
    0.94
    Activations Density 0.211%

    No Known Activations