© 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. 56028
    Prev
    Next
    INDEX
    Explanations

    detecting [Title/Domain] of

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

    The neuron detects titles or phrases of the form “Master / Mistress of ….”

    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
    рую
    -0.91
    đèn
    -0.84
    Jk
    -0.82
     Dreyfus
    -0.81
     интере
    -0.79
     pamoja
    -0.78
     huwa
    -0.78
    屓
    -0.78
    carbons
    -0.75
    uteur
    -0.74
    POSITIVE LOGITS
     ceremonies
    1.41
     Ceremonies
    1.16
     disaster
    1.09
     disguise
    1.08
     domain
    1.04
    domain
    1.03
    odynamics
    0.94
     cerim
    0.94
     prision
    0.93
    فن
    0.90
    Activations Density 0.017%

    No Known Activations