© 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. 60570
    Prev
    Next
    INDEX
    Explanations

    these findings or results

    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
     них
    -1.00
     situación
    -0.91
    了一会儿
    -0.89
     them
    -0.85
     их
    -0.85
    ѝ
    -0.84
    ПЕ
    -0.84
    書の
    -0.83
     mereka
    -0.83
     any
    -0.83
    POSITIVE LOGITS
     our
    2.30
     results
    1.98
     these
    1.78
     findings
    1.73
    results
    1.50
     together
    1.40
     våra
    1.30
    ことから
    1.29
     TOGETHER
    1.27
     therefore
    1.27
    Activations Density 0.121%

    No Known Activations