© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128830
    Prev
    Next
    INDEX
    Explanations

    meow and purr sounds

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

    The neuron fires on substrings that form the onomatopoeic cat vocalizations “meow” and “purr.”

    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
    蛧
    -2.53
     aérienne
    -2.28
    녘
    -2.27
    ));
    -2.09
    ();
    -2.08
    ↵
    -2.06
     schermata
    -2.05
    ization
    -2.03
    ());
    -2.00
    			
    -1.99
    POSITIVE LOGITS
    '
    2.14
     戴
    1.98
    %
    1.97
    
    1.86
    "—
    1.84
     液
    1.80
    〬
    1.80
     muut
    1.79
     показывает
    1.79
    的孩子
    1.76
    Activations Density 0.004%

    No Known Activations