© 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. 34-GEMMASCOPE-RES-131K
    7. 58860
    Prev
    Next
    INDEX
    Explanations

    rattle or rat

    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_34/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
    ताब
    -0.76
    コメント
    -0.69
     comentário
    -0.66
     operand
    -0.66
     Belmont
    -0.65
     خواه
    -0.63
     Кол
    -0.63
    コミュニケーション
    -0.63
     coordinated
    -0.62
     trent
    -0.62
    POSITIVE LOGITS
     rattle
    4.78
     rattling
    4.03
     rattles
    4.00
     rattled
    3.64
    ratt
    3.00
     Ratt
    2.97
     ratt
    2.94
     Rat
    2.56
    rat
    2.22
    Rat
    1.98
    Activations Density 0.056%

    No Known Activations