© 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. 47163
    Prev
    Next
    INDEX
    Explanations

    cell and formula operations

    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
     vedno
    -0.75
    攒
    -0.75
     testicular
    -0.74
     escritores
    -0.74
     việt
    -0.74
     secrecy
    -0.72
     vklju
    -0.70
    Unspecified
    -0.69
     Angaben
    -0.69
    質問
    -0.69
    POSITIVE LOGITS
     cell
    1.66
     cells
    1.38
    cell
    1.38
     Cell
    1.38
    Cell
    1.37
     formula
    1.30
    formula
    1.28
    CELL
    1.20
     CELL
    1.16
     formulas
    1.15
    Activations Density 0.035%

    No Known Activations