© 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. 10-GEMMASCOPE-RES-131K
    7. 110547
    Prev
    Next
    INDEX
    Explanations

    emerging, short, solution, attempt

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

    The neuron activates on numeric tokens (digits, including integers and decimals).

    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
     balkon
    -2.06
     joueurs
    -1.98
     télécharger
    -1.88
     châssis
    -1.87
     mourir
    -1.86
     Sloveniji
    -1.85
     soucis
    -1.85
     coffre
    -1.84
     tamaños
    -1.82
     dezelve
    -1.82
    POSITIVE LOGITS
     in
    2.66
    There
    2.45
     two
    2.44
    Two
    2.20
    When
    2.19
     for
    2.13
     four
    2.06
    It
    2.06
    They
    2.05
     three
    2.02
    Activations Density 0.035%

    No Known Activations