© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57854
    Prev
    Next
    INDEX
    Explanations

    AI, blockchain, money

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

    The neuron strongly activates on punctuation delimiters—especially colons—marking boundaries in the text.

    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
     teritor
    -0.98
     сс
    -0.97
     individus
    -0.96
     bénéficier
    -0.95
     pommes
    -0.94
    篾
    -0.93
     delicioso
    -0.92
     Tienen
    -0.92
     Jerez
    -0.91
     lehen
    -0.91
    POSITIVE LOGITS
     blockchain
    1.78
     AI
    1.64
     China
    1.40
     Brexit
    1.36
     robots
    1.33
     automation
    1.30
     cryptocurrency
    1.27
     data
    1.27
     Artificial
    1.26
     sustainability
    1.25
    Activations Density 0.106%

    No Known Activations