© 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. 1657
    Prev
    Next
    INDEX
    Explanations

    reserve or reserved

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

    The neuron activates on any form of the word “reserve” (e.g. Reserve, reserve, reserved).

    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
     keramik
    -1.09
    穑
    -0.99
     dreadful
    -0.95
    ྄
    -0.93
     Không
    -0.91
     solicitudes
    -0.90
     criterios
    -0.89
     tamanho
    -0.88
    llten
    -0.87
    dámské
    -0.85
    POSITIVE LOGITS
     Reservation
    1.40
    reserv
    1.28
     RESERV
    1.20
    reservation
    1.19
     Reserved
    1.18
    Reservation
    1.17
     Reserve
    1.16
    reserve
    1.13
     reservation
    1.09
     reserve
    1.07
    Activations Density 0.015%

    No Known Activations