© 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. 79322
    Prev
    Next
    INDEX
    Explanations

    back or rear positions

    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
    лій
    -0.82
    CreditCard
    -0.81
     deveria
    -0.79
     strö
    -0.79
    ዚ
    -0.78
     Flä
    -0.75
    かもしれません
    -0.74
    GRUPO
    -0.74
    containsKey
    -0.73
    countryCode
    -0.73
    POSITIVE LOGITS
     back
    6.94
    back
    3.94
     rear
    3.66
    Back
    3.66
     BACK
    3.20
     front
    3.19
    BACK
    3.17
     Back
    2.95
     backside
    2.64
     зад
    2.53
    Activations Density 0.039%

    No Known Activations