© 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. 10-GEMMASCOPE-RES-131K
    7. 14829
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron activates on numeric tokens—years, dates, times, phone‐number digits, percentages, and other number sequences.

    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
     cukru
    -2.14
    因為
    -1.98
     ricas
    -1.70
     katholischen
    -1.66
     these
    -1.66
     Unterstützung
    -1.63
     christlichen
    -1.63
    Dlaczego
    -1.62
    gorro
    -1.60
     resina
    -1.55
    POSITIVE LOGITS
     vó
    1.73
    fourths
    1.67
    astify
    1.63
     موبایل
    1.55
    仍在
    1.52
    庠
    1.52
    meneu
    1.51
     will
    1.48
     alcun
    1.46
     HAST
    1.45
    Activations Density 0.099%

    No Known Activations