© 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. 30460
    Prev
    Next
    INDEX
    Explanations

    zone

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

    The neuron flags occurrences of the word “zone” (in any context or casing).

    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
     uovo
    -1.06
     cervello
    -1.03
     voegen
    -1.03
     fatta
    -1.01
     orgánico
    -0.99
     zelve
    -0.95
     valoraciones
    -0.95
     erlä
    -0.94
     antwortete
    -0.94
     gezondheid
    -0.94
    POSITIVE LOGITS
     Zone
    1.51
    Zone
    1.43
     zon
    1.30
    zone
    1.30
     Zona
    1.23
    Zona
    1.18
     zone
    1.14
     Zon
    1.12
     zones
    1.06
     ZONE
    1.04
    Activations Density 0.013%

    No Known Activations