© 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. 62757
    Prev
    Next
    INDEX
    Explanations

    to be a

    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
    Not in Any Lists

    No Comments

    Negative Logits
     DELLA
    -0.83
    patron
    -0.77
    seid
    -0.75
    DataLoader
    -0.75
    Caixa
    -0.75
     SCIENT
    -0.74
    Skal
    -0.74
    programmer
    -0.73
     verke
    -0.72
    
    -0.70
    POSITIVE LOGITS
     salt
    1.10
     light
    1.02
     testimony
    0.99
     difference
    0.97
     witnesses
    0.94
     examples
    0.93
     thermostat
    0.93
    tificates
    0.92
    light
    0.90
     Difference
    0.90
    Activations Density 0.014%

    No Known Activations