© 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. 128496
    Prev
    Next
    INDEX
    Explanations

    campus locations

    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
    
    -2.14
    銫
    -2.11
    mêmes
    -2.09
     AÑO
    -2.05
    梛
    -2.03
    甃
    -2.03
     Fotografía
    -1.99
     pretože
    -1.98
     Artículo
    -1.97
    
    -1.92
    POSITIVE LOGITS
    -
    3.00
    i
    2.53
    </sup>
    2.52
    l
    2.42
     habe
    2.36
    ↵↵
    2.23
     zwing
    2.23
    b
    2.19
    in
    2.09
     ook
    2.09
    Activations Density 0.005%

    No Known Activations