© 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. 29046
    Prev
    Next
    INDEX
    Explanations

    string replacement regex

    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
     vidrio
    -1.55
     empêcher
    -1.55
    之战
    -1.50
    🛶
    -1.48
     iluminación
    -1.48
    阄
    -1.48
     golpea
    -1.47
     réve
    -1.47
     impulsar
    -1.44
    ？？
    -1.41
    POSITIVE LOGITS
     the
    1.81
    ↵
    1.80
    ?
    1.52
    Likewise
    1.52
     about
    1.45
    those
    1.43
    …
    1.41
     each
    1.38
     사람
    1.37
    Somebody
    1.37
    Activations Density 0.028%

    No Known Activations