© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25677
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    The neuron activates on numerical tokens—years, dates, volumes, percentages, and other 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_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
     beoor
    -0.95
     nemici
    -0.94
    いかが
    -0.93
     giusti
    -0.88
    ポチ
    -0.88
     utilizzati
    -0.86
    tomy
    -0.86
     afirmar
    -0.84
     alcanzado
    -0.84
     verschillende
    -0.84
    POSITIVE LOGITS
     including
    1.03
     менее
    1.00
     will
    0.93
     doGet
    0.90
    าท
    0.89
    deepcopy
    0.88
     ilustrasi
    0.85
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.84
     kommit
    0.84
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.82
    Activations Density 0.177%

    No Known Activations