© 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. 47196
    Prev
    Next
    INDEX
    Explanations

    HTTP requests and responses

    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
    tainen
    -0.82
     Plaque
    -0.71
    ео
    -0.68
     Lumb
    -0.68
    ição
    -0.66
    Luc
    -0.66
     Grin
    -0.66
     Malik
    -0.65
    edo
    -0.65
     Luc
    -0.64
    POSITIVE LOGITS
     namin
    0.73
    lifted
    0.73
    werb
    0.72
    cannabis
    0.71
    Handled
    0.69
    יפול
    0.69
    feuille
    0.67
    *'
    0.67
    Marshal
    0.66
     Loretta
    0.66
    Activations Density 0.097%

    No Known Activations