© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34657
    Prev
    Next
    INDEX
    Explanations

    acceptance or requirements

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

    The neuron fires on quantitative or transactional terms—numbers, measures, currency units, and other tokens that convey amounts or pricing information.

    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
    ospor
    -0.95
     lepro
    -0.89
     pilihan
    -0.86
     Duca
    -0.85
    poll
    -0.85
     hansen
    -0.81
     begründet
    -0.80
    完成です
    -0.79
     stdout
    -0.79
    Drip
    -0.78
    POSITIVE LOGITS
     requirements
    1.16
    要求
    1.13
     receptive
    1.02
     acceptable
    1.02
     preferred
    1.01
    接受
    0.99
     recep
    0.97
     acceptance
    0.96
     prefer
    0.96
    acceptance
    0.94
    Activations Density 0.081%

    No Known Activations