© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95420
    Prev
    Next
    INDEX
    Explanations

    code punctuation and keywords

    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_22/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
     kock
    -1.16
     kommunik
    -1.14
     kül
    -1.12
    Halaman
    -1.08
     burgeoning
    -1.04
     noastre
    -1.04
    思います
    -1.01
    gambarkan
    -1.00
    jelasan
    -0.98
     kollek
    -0.98
    POSITIVE LOGITS
    ↵↵
    1.16
    ");
    1.02
     akşam
    1.02
    )}
    
    0.98
    ISHOP
    0.95
    が終わ
    0.95
    ()/
    0.93
    ]));
    
    0.93
     geçti
    0.92
    lesque
    0.91
    Activations Density 0.015%

    No Known Activations