© 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. 56909
    Prev
    Next
    INDEX
    Explanations

    technical reports index

    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
     any
    -0.90
     meticulously
    -0.82
    见面
    -0.81
     companies
    -0.78
     securing
    -0.78
     all
    -0.77
    usahaan
    -0.76
     maintain
    -0.76
     Հ
    -0.76
    馴
    -0.75
    POSITIVE LOGITS
     NOAA
    1.30
    Publication
    1.15
    abuhan
    1.08
    NOAA
    1.05
     publication
    1.04
     Crear
    1.02
    küche
    0.98
     kèo
    0.98
     couteau
    0.97
     parlement
    0.97
    Activations Density 0.001%

    No Known Activations