© 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. 34-GEMMASCOPE-RES-131K
    7. 31891
    Prev
    Next
    INDEX
    Explanations

    skilled independent visas

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

    The main thing this neuron does is pick out real‐estate listing jargon and metadata (e.g. “Home,” “Estate/Estates,” “Features:,” “Buy,” “freestanding,” etc.).

    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
     consentement
    -0.82
    Vr
    -0.81
    fandom
    -0.77
    #{
    -0.75
    MAI
    -0.74
     Shasta
    -0.72
    ianus
    -0.71
     riveted
    -0.71
    Enfant
    -0.71
     cathédrale
    -0.71
    POSITIVE LOGITS
     Display
    0.94
     contemporáneo
    0.80
     Alf
    0.78
     alf
    0.77
     sich
    0.77
    Render
    0.77
     Kelly
    0.76
     SMS
    0.75
     design
    0.74
     display
    0.74
    Activations Density 0.006%

    No Known Activations