© 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. 22-GEMMASCOPE-RES-131K
    7. 32948
    Prev
    Next
    INDEX
    Explanations

    ensure sewing

    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_22/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
    일에
    -1.16
    reset
    -0.97
     aho
    -0.97
    thral
    -0.96
     ">=
    -0.95
     sibi
    -0.94
    posing
    -0.94
    arischen
    -0.93
     rubio
    -0.93
     Cabello
    -0.93
    POSITIVE LOGITS
     such
    1.20
     recently
    1.20
     Therefore
    1.16
     some
    1.13
     fondamentali
    1.06
     many
    1.04
     all
    1.02
     recientemente
    1.00
    Recently
    0.98
    pullover
    0.98
    Activations Density 0.089%

    No Known Activations