© 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. 47372
    Prev
    Next
    INDEX
    Explanations

    Wave

    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
     ramifications
    -0.83
    niť
    -0.79
     упомина
    -0.75
     TBA
    -0.73
     flak
    -0.71
    ógicos
    -0.70
     mencion
    -0.69
    DataPropertyName
    -0.69
     mention
    -0.68
     neutralize
    -0.67
    POSITIVE LOGITS
     Wave
    1.34
     wave
    1.21
    Wave
    1.20
    wave
    1.13
     Waves
    1.12
     вол
    1.09
     waves
    1.02
    Waves
    0.92
    耦
    0.88
    WAVE
    0.86
    Activations Density 0.012%

    No Known Activations