© 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. 16501
    Prev
    Next
    INDEX
    Explanations

    wrong with something

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

    The neuron is strongly activated by occurrences of the swear‐word “ass” (including masked forms like “a$$es”).

    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
     encender
    -1.41
     colgar
    -1.27
     llorar
    -1.17
    ükü
    -1.15
     moverse
    -1.09
    *{-
    -1.09
    ITCHEN
    -1.07
     fijar
    -1.05
     traer
    -1.05
     هستند
    -1.04
    POSITIVE LOGITS
     it
    2.44
     of
    2.27
     them
    1.73
     about
    1.56
     these
    1.50
     this
    1.40
     on
    1.38
     then
    1.24
     there
    1.13
    apropri
    1.09
    Activations Density 0.136%

    No Known Activations