© 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. 45734
    Prev
    Next
    INDEX
    Explanations

    programming code delimiters

    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
     the
    -2.05
     restoran
    -1.58
     ciepła
    -1.49
     μπορεί
    -1.47
     halus
    -1.46
    -...
    -1.44
    Bukan
    -1.44
     strategis
    -1.41
     sanat
    -1.40
     chini
    -1.40
    POSITIVE LOGITS
     vorliegenden
    1.97
     república
    1.87
    rira
    1.80
    doir
    1.74
     nación
    1.72
    jenigen
    1.71
     toujours
    1.70
    忤
    1.68
     to
    1.66
    licability
    1.63
    Activations Density 0.018%

    No Known Activations