© 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. 30118
    Prev
    Next
    INDEX
    Explanations

    convince, persuade, dissuade

    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
     Plata
    -0.80
     diſt
    -0.72
    /%
    -0.71
     Datum
    -0.70
     FormData
    -0.69
    nościo
    -0.69
    thanol
    -0.69
    ſe
    -0.69
    tifier
    -0.68
    кров
    -0.68
    POSITIVE LOGITS
     convince
    5.19
     convincing
    4.63
     convinced
    4.63
     convinces
    4.25
     persuade
    4.22
     persuaded
    4.06
     persuading
    3.53
     convencer
    3.50
     persuasion
    3.41
     convin
    3.31
    Activations Density 0.058%

    No Known Activations