© 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. 10557
    Prev
    Next
    INDEX
    Explanations

    that that

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

    The neuron activates on numeric tokens (particularly multi‐digit numbers) in the text.

    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
     our
    -2.33
    heureusement
    -1.95
     whose
    -1.92
     stating
    -1.89
     burgeoning
    -1.87
     superbly
    -1.84
     makeshift
    -1.81
     иногда
    -1.79
     может
    -1.77
     during
    -1.73
    POSITIVE LOGITS
     müsse
    2.02
    。
    2.00
     houve
    1.84
     könne
    1.78
     startling
    1.76
    也不
    1.75
    ervant
    1.71
     exceedingly
    1.65
     astonishing
    1.62
    ifying
    1.59
    Activations Density 0.007%

    No Known Activations