© 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. 90362
    Prev
    Next
    INDEX
    Explanations

    technical proposals and specifications

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

    The neuron primarily activates on numeric tokens (e.g. version numbers and other digit sequences) in technical 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
    цина
    -0.71
    reply
    -0.71
     trigger
    -0.70
    jsdelivr
    -0.65
    Photo
    -0.64
    おく
    -0.63
     remot
    -0.63
     Antworten
    -0.63
    testo
    -0.62
     truthful
    -0.61
    POSITIVE LOGITS
     proposal
    2.34
     proposals
    2.17
     Proposal
    1.98
     Proposals
    1.88
    proposal
    1.88
    Proposal
    1.84
    Proposals
    1.70
     RFC
    1.67
    proposals
    1.66
    提案
    1.63
    Activations Density 0.091%

    No Known Activations