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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12625
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

    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_10/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
    ſten
    -2.61
     Publicar
    -2.33
    ✇
    -2.30
    崀
    -2.30
    
    -2.30
     comunica
    -2.19
     adesivo
    -2.19
     tocado
    -2.17
    
    -2.16
     alojamientos
    -2.14
    POSITIVE LOGITS
    :
    2.39
    .
    2.38
    )
    2.30
    /
    2.30
     during
    2.22
     phenomenal
    2.14
     although
    2.09
    ...
    2.09
    -
    2.09
    f
    2.06
    Activations Density 0.004%

    No Known Activations