© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92318
    Prev
    Next
    INDEX
    Explanations

    numbers ending in iiii

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

    The neuron activates on multi‐digit numeric tokens (particularly years and other three‐ or four‐digit numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     so
    -1.53
     such
    -1.24
     сейчас
    -1.10
     cannot
    -1.09
    Since
    -1.05
    ၀
    -1.03
    鹈
    -1.02
    Then
    -1.01
    Every
    -1.00
     every
    -0.98
    POSITIVE LOGITS
    iiii
    1.09
    ITHER
    1.02
    iiiiiiii
    1.02
     bascul
    1.01
     doman
    0.97
    ckeye
    0.96
    verläs
    0.96
     exceptional
    0.96
    rf
    0.95
    enie
    0.94
    Activations Density 0.094%

    No Known Activations