© 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. 25289
    Prev
    Next
    INDEX
    Explanations

    sequence of events and time

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

    This neuron fires on tokens that look like named‐entity labels—especially numbers, dates, monetary amounts, and other capitalized/name-like tokens.

    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
     from
    -1.24
     these
    -1.21
     those
    -1.10
     åren
    -1.09
     annet
    -1.02
     dager
    -1.02
     frågan
    -1.00
     explicado
    -0.98
     даже
    -0.97
     infek
    -0.97
    POSITIVE LOGITS
     then
    2.06
     eventually
    1.35
    Entonces
    1.30
     Luego
    1.26
     later
    1.22
     Empieza
    1.20
    Then
    1.19
     Mejora
    1.17
     Añade
    1.17
     subsequently
    1.17
    Activations Density 0.062%

    No Known Activations