© 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. 56896
    Prev
    Next
    INDEX
    Explanations

    what kind of

    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
    こんばん
    -0.98
     bienfaits
    -0.92
     १
    -0.92
     baig
    -0.91
    معرفی
    -0.91
    тился
    -0.90
    ྩ
    -0.90
    こんばんは
    -0.90
    どうしても
    -0.89
    otropy
    -0.88
    POSITIVE LOGITS
     clothes
    1.34
     kind
    1.33
     shape
    1.30
     skills
    1.28
     shoes
    1.27
     questions
    1.24
     problems
    1.22
     changes
    1.22
     impact
    1.22
     things
    1.19
    Activations Density 0.015%

    No Known Activations