© 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. 106356
    Prev
    Next
    INDEX
    Explanations

    list separators and conjunctions

    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
     pantolon
    -1.92
     hırka
    -1.84
    錾
    -1.79
     écrire
    -1.78
     vôtre
    -1.76
     délais
    -1.73
     exprimer
    -1.72
     corriger
    -1.72
     montrer
    -1.70
     maniere
    -1.68
    POSITIVE LOGITS
     and
    6.53
     as
    2.89
     plus
    2.84
    以及
    2.72
     along
    2.70
     or
    2.47
     etc
    2.45
     which
    2.45
     sowie
    2.28
     a
    2.13
    Activations Density 0.203%

    No Known Activations