© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 16470
    Prev
    Next
    INDEX
    Explanations

    positive classifications

    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
     discer
    -1.12
     acclaimed
    -1.05
     decidedly
    -1.00
     masterful
    -0.96
     NINE
    -0.92
    𝓚
    -0.90
    ïti
    -0.90
     EIGHT
    -0.89
     magnificent
    -0.89
     tumultuous
    -0.87
    POSITIVE LOGITS
     for
    1.09
     their
    1.07
     by
    1.06
     with
    0.97
     first
    0.96
     all
    0.96
     HUGE
    0.94
     helped
    0.92
     any
    0.91
     two
    0.90
    Activations Density 0.021%

    No Known Activations