© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41078
    Prev
    Next
    INDEX
    Explanations

    code, print, list

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

    The neuron specifically detects Python print 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
     every
    -1.41
     or
    -1.37
    [
    -1.35
     csak
    -1.32
    In
    -1.31
     only
    -1.27
     before
    -1.27
    궤
    -1.26
     culturelles
    -1.26
    Only
    -1.26
    POSITIVE LOGITS
    
    1.86
    趼
    1.83
     "
    1.75
    </em>
    1.70
     BECAUSE
    1.55
     οποίο
    1.55
    €”
    1.54
    umbered
    1.51
     andere
    1.43
    睃
    1.42
    Activations Density 0.027%

    No Known Activations