© 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. 22-GEMMASCOPE-RES-131K
    7. 27719
    Prev
    Next
    INDEX
    Explanations

    saving artifacts and checkpoints

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

    The neuron activates on words and tokens related to saving or persisting (e.g. save, save_model, format, h5, checkpoint, publish).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.02
    getSystemService
    -1.01
     European
    -1.01
     сочи
    -1.00
     /
    -1.00
    autoreleasepool
    -0.98
     Its
    -0.98
     deren
    -0.95
     Help
    -0.95
    花园
    -0.95
    POSITIVE LOGITS
    Arbe
    1.45
    呯
    1.35
    我们
    1.23
    おわりに
    1.17
    Morfo
    1.14
     vocale
    1.12
     vaše
    1.11
    стойчи
    1.09
     backups
    1.08
     prestigio
    1.06
    Activations Density 0.003%

    No Known Activations