© 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. 106320
    Prev
    Next
    INDEX
    Explanations

    Question starts or date starts

    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
     other
    -1.03
     Because
    -1.00
     Since
    -0.96
     so
    -0.95
     Autres
    -0.94
     During
    -0.93
     another
    -0.92
     With
    -0.91
     every
    -0.91
     get
    -0.90
    POSITIVE LOGITS
    naire
    0.98
     nœ
    0.98
    usually
    0.98
    ikh
    0.96
     meistens
    0.94
    ITABLE
    0.94
    nels
    0.94
     angewendet
    0.93
     telo
    0.93
    mostly
    0.91
    Activations Density 0.000%

    No Known Activations