© 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. 69953
    Prev
    Next
    INDEX
    Explanations

    saving code

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

    The neuron flags occurrences of “save” (e.g. save, save!, save()) method calls in code.

    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
    嚒
    -1.73
    蟊
    -1.63
     deras
    -1.63
     ſec
    -1.60
    ⎔
    -1.59
    鼍
    -1.57
     laisser
    -1.57
    ep
    -1.54
     teo
    -1.54
    particularly
    -1.51
    POSITIVE LOGITS
     through
    1.98
     without
    1.96
     regarding
    1.88
     concerning
    1.84
     could
    1.80
     Hundreds
    1.77
     Despite
    1.75
    Perhaps
    1.74
     does
    1.72
     Currently
    1.70
    Activations Density 0.004%

    No Known Activations