© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72493
    Prev
    Next
    INDEX
    Explanations

    code structure and errors

    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
     москва
    -1.00
     وغير
    -0.96
     autres
    -0.96
    everywhere
    -0.96
    tività
    -0.96
     mondi
    -0.96
     fortæ
    -0.94
    décoration
    -0.88
     dát
    -0.88
     rapporter
    -0.88
    POSITIVE LOGITS
     similar
    0.87
     erwähnt
    0.84
     include
    0.84
    jenige
    0.83
     instead
    0.78
     if
    0.77
    山西
    0.77
     linked
    0.77
    ristiano
    0.77
     GoFundMe
    0.77
    Activations Density 0.003%

    No Known Activations