© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78737
    Prev
    Next
    INDEX
    Explanations

    self-service kiosks and terminals

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

    The neuron fires strongly on terminology related to automated or self-service systems—words like “self-service,” “unattended,” “terminal,” “kiosk,” and “check-in.”

    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
    becue
    -0.87
    🔱
    -0.85
    Teléfono
    -0.85
     Skyscanner
    -0.82
     Sonar
    -0.82
     Telef
    -0.81
     Atalanta
    -0.81
    nastics
    -0.81
    Calendario
    -0.80
     cappella
    -0.80
    POSITIVE LOGITS
     self
    2.31
     kiosk
    2.08
     kios
    1.86
     Self
    1.65
     touch
    1.63
    Self
    1.46
     contactless
    1.45
     scan
    1.43
    self
    1.41
     QR
    1.41
    Activations Density 0.024%

    No Known Activations