© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39710
    Prev
    Next
    INDEX
    Explanations

    code structures and data references

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

    The neuron selectively activates on numeric literal tokens (decimal numbers) in code snippets.

    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
    These
    -1.12
    很快就
    -1.00
    Sådan
    -0.97
    Leírás
    -0.96
    ંગ
    -0.91
    рочный
    -0.90
    inderung
    -0.90
     herself
    -0.90
    Weitere
    -0.86
    verengi
    -0.86
    POSITIVE LOGITS
     their
    1.59
    其
    1.23
     its
    1.16
     (
    0.99
     rayures
    0.99
    łącz
    0.97
     его
    0.96
    ⌀
    0.95
     ње
    0.95
     they
    0.93
    Activations Density 0.011%

    No Known Activations