© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64251
    Prev
    Next
    INDEX
    Explanations

    places, things, or contexts

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

    The neuron strongly activates on substantive content words—especially concrete, topic-carrying nouns (e.g. “set,” “restaurants,” “guides,” “rooms,” “cells,” “skin”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     पढ़ें
    -1.05
     footballer
    -1.00
     then
    -0.98
     traditionnels
    -0.97
     млн
    -0.96
     /*
    -0.95
    ých
    -0.95
    IMPORTED
    -0.95
     eeuw
    -0.94
     since
    -0.94
    POSITIVE LOGITS
     of
    1.14
     that
    1.08
     robusto
    1.03
     nạ
    0.95
    却被
    0.94
     pocz
    0.93
     constater
    0.91
    éroport
    0.90
     burbu
    0.89
     Realism
    0.89
    Activations Density 0.223%

    No Known Activations