© 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. 62399
    Prev
    Next
    INDEX
    Explanations

    can and cannot

    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
    :''
    -0.90
     rés
    -0.88
    šin
    -0.87
    паси
    -0.84
    炽
    -0.82
    doll
    -0.81
     député
    -0.80
    inches
    -0.79
     cromado
    -0.79
     energia
    -0.78
    POSITIVE LOGITS
     not
    1.15
     clearly
    1.02
    Not
    0.96
     roughly
    0.94
     easily
    0.94
     barely
    0.91
     already
    0.91
    初步
    0.88
     only
    0.86
    ことが
    0.85
    Activations Density 0.008%

    No Known Activations