© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85855
    Prev
    Next
    INDEX
    Explanations

    Algeria country codes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on the letter sequence “dz” (i.e. tokens containing “dz”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    </sub>
    -3.94
    </h3>
    -3.69
    i
    -2.78
    ";
    -2.59
    </blockquote>
    -2.42
    。“
    -2.39
    盌
    -2.31
    </strong>
    -2.28
    );
    -2.22
    结语
    -2.22
    POSITIVE LOGITS
    </b>
    2.70
     \&
    2.58
    犼
    2.14
    ():
    
    2.11
     становятся
    2.09
    \
    2.09
     проходят
    2.06
    気に入りの
    2.00
    )):
    
    1.99
    AutoresizingMask
    1.93
    Activations Density 0.004%

    No Known Activations