© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75064
    Prev
    Next
    INDEX
    Explanations

    historical records and early items

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

    The neuron detects numeric tokens—especially years, dates, and other multi‐digit number strings.

    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
     جدید
    -1.16
    鳕
    -1.05
    キュリティ
    -1.02
     kilo
    -0.95
     philo
    -0.95
     keç
    -0.94
     latest
    -0.92
    cions
    -0.91
    preneurs
    -0.91
     ২০১
    -0.90
    POSITIVE LOGITS
     early
    1.30
    当時の
    1.20
     from
    1.13
     forgotten
    1.12
     Depression
    1.09
    ਿਆ
    1.09
     temprana
    1.08
     earliest
    1.05
    inkl
    1.03
    odotus
    1.02
    Activations Density 0.114%

    No Known Activations