© 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. 22-GEMMASCOPE-RES-131K
    7. 13584
    Prev
    Next
    INDEX
    Explanations

    arena or Ari names

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

    The neuron activates on tokens containing the substring “ari,” e.g. in words like “arena,” “arith,” “Ari,” or “Arizona.”

    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
    ’
    -3.45
    艽
    -3.00
    la
    -2.55
    鹮
    -2.48
    のが
    -2.33
    ぁ
    -2.31
     utilizzata
    -2.20
    袛
    -2.19
     dubbio
    -2.17
    馐
    -2.09
    POSITIVE LOGITS
    ↵↵
    2.42
    不错的
    2.22
     â
    2.11
     are
    2.09
    prime
    2.08
    发生的
    1.97
     sokak
    1.95
     symboli
    1.94
     unambiguous
    1.91
     persuading
    1.91
    Activations Density 0.037%

    No Known Activations