© 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. 16382
    Prev
    Next
    INDEX
    Explanations

    programming conditional statements

    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
    return
    -1.00
    hängigkeit
    -0.86
    dann
    -0.83
     ekst
    -0.83
     koron
    -0.82
    .”
    -0.81
     eduk
    -0.80
     kome
    -0.80
     karbon
    -0.80
     return
    -0.79
    POSITIVE LOGITS
     altrimenti
    1.05
     maupun
    1.04
     această
    1.03
     otomatis
    0.96
     istnie
    0.96
     trzyma
    0.96
     pręd
    0.94
     betrekking
    0.94
     chwil
    0.91
    ところに
    0.90
    Activations Density 0.002%

    No Known Activations