© 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. 10-GEMMASCOPE-RES-131K
    7. 68524
    Prev
    Next
    INDEX
    Explanations

    life and day events

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     veľa
    -1.74
     neumáticos
    -1.47
     čier
    -1.46
    ఱ
    -1.45
     síntesis
    -1.45
    irability
    -1.45
     ľudí
    -1.42
     obyvateľov
    -1.41
     redacción
    -1.39
     ficando
    -1.39
    POSITIVE LOGITS
     Then
    1.42
     used
    1.37
     a
    1.35
    :
    1.28
     impacto
    1.23
    了一個
    1.20
     sorta
    1.17
    Then
    1.16
     clog
    1.13
     chose
    1.12
    Activations Density 0.046%

    No Known Activations