© 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. 57114
    Prev
    Next
    INDEX
    Explanations

    initialisms and specific terms

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

    The neuron is triggered by uppercase acronyms, gene/protein names, and other technical initialisms or proper‐noun tokens.

    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
    .”
    -1.00
     freundlichen
    -0.99
    tréal
    -0.98
    *~*~
    -0.97
    ifflin
    -0.97
    需要
    -0.96
    liseum
    -0.96
     minimizar
    -0.96
     materialism
    -0.96
    די
    -0.95
    POSITIVE LOGITS
     Madness
    1.93
     Mayhem
    1.91
     mayhem
    1.51
     Mondays
    1.28
    讥
    1.26
     madness
    1.26
     terceira
    1.18
    〈
    1.14
     η
    1.09
    angelo
    1.05
    Activations Density 0.288%

    No Known Activations