© 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. 62614
    Prev
    Next
    INDEX
    Explanations

    retry or try again

    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
     mieście
    -0.77
    tése
    -0.77
    world
    -0.73
     simultaneous
    -0.73
    ROUT
    -0.71
     wrench
    -0.71
     eradicated
    -0.71
     ahead
    -0.70
    exercice
    -0.70
    ształ
    -0.69
    POSITIVE LOGITS
     retry
    1.84
     exponential
    1.48
     Retry
    1.37
    retry
    1.36
     Exponential
    1.30
    BACK
    1.27
    Exponential
    1.25
    Retry
    1.24
    exponential
    1.24
     back
    1.23
    Activations Density 0.034%

    No Known Activations