© 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. 29992
    Prev
    Next
    INDEX
    Explanations

    legal cases with minors

    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
     thankful
    -0.86
     thanks
    -0.81
     Thanks
    -0.77
     dankbar
    -0.74
    {!!
    -0.73
     thanking
    -0.73
     gracias
    -0.72
    ffee
    -0.72
    чью
    -0.71
    thanks
    -0.71
    POSITIVE LOGITS
     request
    0.70
     terrestres
    0.69
    request
    0.68
    JN
    0.68
    fiscal
    0.68
     foglal
    0.68
    teri
    0.67
    azer
    0.67
    Computation
    0.66
    editar
    0.65
    Activations Density 0.026%

    No Known Activations