© 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. 29929
    Prev
    Next
    INDEX
    Explanations

    they followed by verbs

    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
     bude
    -1.56
    tya
    -1.52
    larda
    -1.52
     می‌تواند
    -1.48
     может
    -1.36
     kendini
    -1.35
     будет
    -1.35
     〜
    -1.34
     graciosos
    -1.34
     yeni
    -1.30
    POSITIVE LOGITS
     are
    5.53
     were
    3.34
     have
    2.80
     aren
    2.48
     weren
    2.14
     themselves
    2.05
     don
    1.91
     serão
    1.71
     haven
    1.66
    are
    1.63
    Activations Density 0.082%

    No Known Activations