© 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. 32736
    Prev
    Next
    INDEX
    Explanations

    domain endings

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

    The neuron detects parts of web addresses—particularly top‐level domain tokens (e.g. “.org”, “.com”, “.gov”, “.tv”, “.cn”).

    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
     VERY
    -1.34
    ৢ
    -1.28
    泐
    -1.22
    
    -1.20
    mettre
    -1.19
     unbelievably
    -1.19
     Algunas
    -1.18
     utilisés
    -1.17
     incredibly
    -1.16
     triko
    -1.16
    POSITIVE LOGITS
    Transk
    1.21
    Jeudi
    1.18
     first
    1.17
     or
    1.13
    Lundi
    1.11
     शुर
    1.04
    Dimanche
    1.02
    aneity
    0.99
    เกง
    0.98
    原来的
    0.98
    Activations Density 0.017%

    No Known Activations