© 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. 22-GEMMASCOPE-RES-131K
    7. 35496
    Prev
    Next
    INDEX
    Explanations

    foreign language titles and years

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

    The neuron consistently lights up on 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
    ळ
    -1.03
     fabrik
    -1.01
    parently
    -0.99
     ὅ
    -0.98
     herbes
    -0.97
    bestos
    -0.97
     составляет
    -0.97
     puas
    -0.96
    ⟨
    -0.96
    ﴿
    -0.96
    POSITIVE LOGITS
     also
    1.02
    ্ম
    0.99
     essence
    0.98
     growl
    0.96
     various
    0.95
     verschillende
    0.91
     potrivit
    0.90
     perfeito
    0.88
     diferite
    0.88
     Könige
    0.85
    Activations Density 0.022%

    No Known Activations