© 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. 56758
    Prev
    Next
    INDEX
    Explanations

    film and media descriptions

    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
     paulista
    -0.79
    worldly
    -0.79
     Si
    -0.78
    hér
    -0.78
     colours
    -0.76
     collecting
    -0.73
     bullet
    -0.73
     combat
    -0.71
    miss
    -0.71
    created
    -0.70
    POSITIVE LOGITS
     Notting
    0.96
     Weddings
    0.79
    OLED
    0.79
     Paddington
    0.77
     Vicar
    0.77
    Julia
    0.76
    geführten
    0.75
    భ
    0.74
     Punjabi
    0.74
     Bharat
    0.74
    Activations Density 0.015%

    No Known Activations