© 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. 83192
    Prev
    Next
    INDEX
    Explanations

    prefixes after hyphens

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

    This neuron responds to parenthetical and bracket markers (i.e. “(”, “)”, “[”, “]”).

    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
    初めての
    -0.94
    狭い
    -0.88
    Conce
    -0.88
     stolet
    -0.84
    后期
    -0.84
    貴重な
    -0.84
    身后的
    -0.83
    Espec
    -0.82
     commended
    -0.79
    理由は
    -0.79
    POSITIVE LOGITS
     prefix
    1.09
    kilo
    1.05
    hemi
    1.02
     nano
    1.01
    epi
    1.01
    ANTI
    1.00
     mono
    0.99
    Semi
    0.97
     Semi
    0.96
     prefixes
    0.95
    Activations Density 0.096%

    No Known Activations