© 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. 99633
    Prev
    Next
    INDEX
    Explanations

    relative clauses

    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
     multitude
    -2.00
     plethora
    -1.83
    there
    -1.77
     nahezu
    -1.76
     perplexing
    -1.72
     menyebut
    -1.69
    逦
    -1.68
     skóra
    -1.66
     burgeoning
    -1.63
     sooooo
    -1.59
    POSITIVE LOGITS
    螃
    1.68
    ↵
    1.67
    1.65
    やや
    1.63
    ឵
    1.60
    ⚋
    1.55
    A
    1.52
    –
    1.52
    饜
    1.52
     Quien
    1.52
    Activations Density 0.001%

    No Known Activations