© 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. 66644
    Prev
    Next
    INDEX
    Explanations

    lists separated by and or

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

    This neuron does not detect any patterns in the input—it remains inactive (all activations zero).

    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
    えっ
    -1.23
    擽
    -1.20
    盌
    -1.16
    あぁ
    -1.11
    あー
    -1.08
    殽
    -1.08
     excesso
    -1.07
    byr
    -1.06
     både
    -1.06
    urna
    -1.05
    POSITIVE LOGITS
    <bos>
    1.45
     Gegenteil
    0.99
    一大
    0.94
     [],
    0.90
     J
    0.88
     venerable
    0.88
     यहां
    0.86
     Martin
    0.86
     R
    0.85
    Man
    0.85
    Activations Density 0.065%

    No Known Activations