© 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. 106275
    Prev
    Next
    INDEX
    Explanations

    code file paths

    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
    GAP
    -0.84
     GAP
    -0.76
    prix
    -0.72
     gap
    -0.71
    pumpe
    -0.68
    Gap
    -0.68
    stä
    -0.68
    öszi
    -0.67
    divide
    -0.67
     content
    -0.65
    POSITIVE LOGITS
    かし
    0.69
     vane
    0.67
     Dimitri
    0.67
     Bens
    0.67
    Bounds
    0.64
     niacin
    0.63
     ABN
    0.63
     puffs
    0.63
    াল
    0.63
     delirium
    0.62
    Activations Density 0.052%

    No Known Activations