© 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. 308
    Prev
    Next
    INDEX
    Explanations

    storage drives

    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
     ducati
    -1.37
     étranger
    -1.36
     loto
    -1.35
     campi
    -1.34
     peppa
    -1.32
     acci
    -1.32
     
    -1.30
     jopa
    -1.30
    !”,
    -1.28
     vespa
    -1.25
    POSITIVE LOGITS
     "
    1.51
     ๆ
    1.39
    嘎
    1.27
    ).
    1.23
     oder
    1.19
    ,
    1.19
     tha
    1.17
    </b>
    1.16
     him
    1.13
     ist
    1.09
    Activations Density 0.086%

    No Known Activations