© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124691
    Prev
    Next
    INDEX
    Explanations

    propose/proposal

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

    propose or proposal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    是
    0.75
     принима
    0.66
     K
    0.64
    স
    0.64
    п
    0.64
    д
    0.64
    𝘀
    0.63
     meltdown
    0.62
     D
    0.61
    擔心
    0.61
    POSITIVE LOGITS
     proposta
    0.90
    Proposed
    0.88
     proposals
    0.86
     propuesta
    0.82
    提案
    0.79
    Proposal
    0.79
    Ф
    0.76
     proposes
    0.74
     proposé
    0.74
    Ба
    0.73
    Activations Density 0.033%

    No Known Activations