© 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. 47747
    Prev
    Next
    INDEX
    Explanations

    enabling better outcomes

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

    The neuron flags formal, technical or patent‐style language—especially discourse markers (e.g. “which,” “thereby”), commas, and other hallmarks of dense, procedural writing.

    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
     versátil
    -0.90
    оо
    -0.89
    crity
    -0.88
     deportistas
    -0.87
     melawan
    -0.87
     disponíveis
    -0.86
    краси
    -0.86
     utilisée
    -0.85
     membersihkan
    -0.85
     publiée
    -0.85
    POSITIVE LOGITS
     achieve
    1.56
     realize
    1.52
     effectively
    1.50
     greatly
    1.35
     solve
    1.30
     realizing
    1.30
     better
    1.28
    实现
    1.26
     achieved
    1.25
     realizes
    1.25
    Activations Density 0.078%

    No Known Activations