© 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. 22-GEMMASCOPE-RES-131K
    7. 33559
    Prev
    Next
    INDEX
    Explanations

    nightlife in Kuala Lumpur

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

    The neuron detects those sidebar or header numbers that indicate things like view, comment, or rating counts appearing next to section titles or article headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Brasile
    -1.02
     magis
    -1.01
    ciamento
    -0.95
     following
    -0.94
     fett
    -0.91
     kuna
    -0.91
     vasca
    -0.91
     CUTE
    -0.90
     Técnica
    -0.89
    と考えて
    -0.87
    POSITIVE LOGITS
     mariée
    1.14
    UALA
    1.12
     viajes
    1.12
     cantantes
    1.10
     tuvieron
    1.08
     faciles
    1.08
     publiée
    1.07
     jugadores
    1.05
    "],
    0.99
     насељу
    0.98
    Activations Density 0.003%

    No Known Activations