© 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. 79262
    Prev
    Next
    INDEX
    Explanations

    wireless channel fading and distortion

    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
     brotherhood
    -0.75
    oblig
    -0.74
    teger
    -0.74
    assignments
    -0.73
     רג
    -0.73
    ONY
    -0.71
    investigation
    -0.71
     grise
    -0.70
     parli
    -0.70
     cams
    -0.69
    POSITIVE LOGITS
     fading
    1.37
     channel
    1.29
     Channel
    1.16
    Channel
    1.15
    channel
    1.10
     shadow
    0.97
    Channels
    0.95
     fade
    0.95
     Channels
    0.93
     Rayleigh
    0.92
    Activations Density 0.037%

    No Known Activations