© 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. 66890
    Prev
    Next
    INDEX
    Explanations

    annotation, spacing, change

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

    The neuron activates on numeric literals (especially multi-digit and decimal numbers).

    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
     Monarchy
    -0.91
     dakota
    -0.87
     Andorra
    -0.86
     indicó
    -0.86
     sagit
    -0.85
     eden
    -0.85
     mám
    -0.84
     egypt
    -0.84
     incen
    -0.84
     EXHIB
    -0.84
    POSITIVE LOGITS
     one
    1.09
     at
    0.95
    ولايات
    0.91
     On
    0.88
     any
    0.87
    hatenablog
    0.85
     These
    0.83
    ABUL
    0.82
     through
    0.82
    Through
    0.80
    Activations Density 0.083%

    No Known Activations