© 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. 25267
    Prev
    Next
    INDEX
    Explanations

    `:variable` or `('variable')`

    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
     Egyes
    -0.97
    logos
    -0.92
    koliv
    -0.91
     Chambres
    -0.90
     getrock
    -0.89
    łeś
    -0.89
    もあった
    -0.88
     mosaico
    -0.88
     elefante
    -0.87
    pecu
    -0.87
    POSITIVE LOGITS
     gracias
    0.94
    :
    0.93
    AN
    0.86
    0.85
     keduanya
    0.85
     *
    0.84
    With
    0.82
     dejar
    0.82
     selbst
    0.81
    )})
    0.81
    Activations Density 0.004%

    No Known Activations