© 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. 10-GEMMASCOPE-RES-131K
    7. 58175
    Prev
    Next
    INDEX
    Explanations

    forming or creating something

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    leqslant
    -1.54
     když
    -1.52
    .&
    -1.52
    餍
    -1.45
     parado
    -1.43
    thats
    -1.41
     eſſ
    -1.35
     atunci
    -1.34
    '
    -1.34
    unless
    -1.34
    POSITIVE LOGITS
    ?”
    2.11
    。”
    1.91
    </em>
    1.90
    ,”
    1.85
    It
    1.70
    Ꮂ
    1.66
    ⚢
    1.65
    While
    1.62
     télévis
    1.59
     –
    1.52
    Activations Density 0.052%

    No Known Activations