© 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. 32782
    Prev
    Next
    INDEX
    Explanations

    dialogue punctuation followed by pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     奶油
    -1.52
    蓠
    -1.40
    _______
    -1.38
    issez
    -1.34
     camiset
    -1.31
    isman
    -1.30
    tonsoft
    -1.27
    媪
    -1.27
     obst
    -1.24
     revela
    -1.22
    POSITIVE LOGITS
    ?
    1.98
     asked
    1.53
    自然是
    1.51
    当然是
    1.38
    Kör
    1.30
    是因为
    1.28
     häufigsten
    1.23
     prompted
    1.23
    0
    1.16
     gött
    1.14
    Activations Density 0.002%

    No Known Activations