© 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. 87190
    Prev
    Next
    INDEX
    Explanations

    regular expression constructs

    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
    ),
    -2.16
     to
    -1.86
    ."
    -1.83
     "
    -1.82
    ));
    -1.70
    },
    -1.70
     is
    -1.67
     ancianos
    -1.63
     (
    -1.59
     ?
    -1.59
    POSITIVE LOGITS
     masques
    1.71
    釹
    1.70
     yetu
    1.59
     Теперь
    1.57
     parma
    1.56
     Amongst
    1.55
    栳
    1.55
     barnet
    1.55
     після
    1.52
     compl
    1.50
    Activations Density 0.007%

    No Known Activations