© 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. 118907
    Prev
    Next
    INDEX
    Explanations

    Power prefix

    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
     trecho
    -0.83
     começaram
    -0.82
    cuisine
    -0.82
     Nobles
    -0.76
    Cuisine
    -0.75
    turismo
    -0.75
    ratios
    -0.75
    recognition
    -0.73
     Cuisine
    -0.71
     devez
    -0.70
    POSITIVE LOGITS
     Power
    1.58
    Power
    1.54
     powerless
    1.41
     power
    1.38
    power
    1.23
    POWER
    1.13
    Powered
    1.13
     POWER
    1.09
    Mockito
    1.05
    powered
    0.90
    Activations Density 0.029%

    No Known Activations