© 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. 22056
    Prev
    Next
    INDEX
    Explanations

    code syntax

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

    The neuron fires on numeric array‐size declarations in code (bracketed literal sizes in array or allocation statements).

    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
    辚
    -2.84
     deliciously
    -2.80
    鶿
    -2.69
    琲
    -2.67
    should
    -2.66
    
    -2.61
    nearly
    -2.53
     recente
    -2.52
     delightfully
    -2.45
     senza
    -2.39
    POSITIVE LOGITS
    ).
    3.23
    ');
    2.66
    );
    2.56
    ];
    2.56
    .”
    2.53
    ))
    2.50
     if
    2.47
     because
    2.44
     incredible
    2.42
     reconoci
    2.42
    Activations Density 0.008%

    No Known Activations