© 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. 33075
    Prev
    Next
    INDEX
    Explanations

    listing conjunctions and items

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

    The neuron fires on numeric tokens—counts, measurements, statistics, and other standalone numbers.

    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
    铙
    -1.17
     huit
    -1.14
    "__
    -1.06
     retirer
    -1.05
     хоте
    -1.05
     couvrir
    -1.00
     vetores
    -1.00
     "--
    -0.99
     accesorios
    -0.99
     accessoire
    -0.99
    POSITIVE LOGITS
     especially
    1.71
    Among
    1.52
     Especially
    1.45
     particularly
    1.41
     While
    1.41
    During
    1.39
     Similarly
    1.39
     Among
    1.37
     other
    1.35
     such
    1.33
    Activations Density 0.105%

    No Known Activations