© 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. 79383
    Prev
    Next
    INDEX
    Explanations

    related products and suggestions

    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
    Cevap
    -1.12
    ừa
    -0.99
    Răsp
    -0.97
    目次
    -0.94
    縂
    -0.94
    Transk
    -0.92
    retung
    -0.89
    Reprodução
    -0.89
    altezza
    -0.88
    賸
    -0.88
    POSITIVE LOGITS
     related
    2.23
     similar
    1.91
    related
    1.88
    Related
    1.71
     other
    1.68
    Similar
    1.67
     Related
    1.54
    similar
    1.49
     επίσης
    1.45
     Similar
    1.43
    Activations Density 0.020%

    No Known Activations