© 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. 34-GEMMASCOPE-RES-131K
    7. 106110
    Prev
    Next
    INDEX
    Explanations

    happen to

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     happened
    -1.38
     happen
    -1.34
     happens
    -1.23
     happening
    -1.09
    happens
    -1.02
    เกิด
    -1.01
    flatMap
    -0.99
    happened
    -0.94
     děti
    -0.90
     übri
    -0.88
    POSITIVE LOGITS
     to
    1.34
     mention
    1.05
     be
    0.95
     berada
    0.85
    ついでに
    0.83
     essere
    0.83
     onto
    0.82
     luck
    0.82
     into
    0.81
    tobe
    0.81
    Activations Density 0.006%

    No Known Activations